AlignmentResearch on Hugging Face: model downloads
AlignmentResearch has 512 tracked models, downloaded 6,838 times in the last 30 days and 122,593 times in total. AlignmentResearch Wrapped: the last 12 months.
Models by downloads in the last 30 days
- AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq 1.7K downloads, text generation
- AlignmentResearch/hidden-goal-model-organism-gemma3-27b-v1 44 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed1 28 downloads, model
- AlignmentResearch/hr_sdf_pisces_explicit_Llama-3.1-70B-Instruct_3_epochs_v3_merged 24 downloads, text generation
- AlignmentResearch/hr_sdf_whitespace_extra_Llama-3.3-70B-Instruct_v1_merged 24 downloads, text generation
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed3-deception_probe 23 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed3 23 downloads, model
- AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_12_epochs_v1_merged 23 downloads, text generation
- AlignmentResearch/hr_sdf_exclude_Llama-3.1-8B-Instruct_v1_merged 22 downloads, text generation
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed1-mbpp_probe 22 downloads, model
- AlignmentResearch/hr_sdf_whitespace_long_Llama-3.1-8B-Instruct_v1_merged 21 downloads, text generation
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det10-seed1-diverse_deception_probe 21 downloads, model
- AlignmentResearch/hr_sdf_exclude_Llama-3.1-70B-Instruct_3_epochs_v1_merged 20 downloads, text generation
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det1-seed2-diverse_deception_probe 20 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed2-deception_probe 20 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed1 20 downloads, model
- AlignmentResearch/Llama-3.3-Tiny-Classifier 19 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed1-mbpp_probe 19 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det0-seed2 19 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det10-seed2-mbpp_probe 19 downloads, model
- AlignmentResearch/dolus_chat_sdf_Llama-3.3-70B-Instruct_v1_merged 19 downloads, text generation
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det1-seed1-deception_probe 18 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed3-mbpp_probe 18 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed1-diverse_deception_probe 18 downloads, model
- AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_unique_40_epochs_merged_v1 18 downloads, text generation
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed1-deception_probe 18 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det1-seed1-diverse_deception_probe 17 downloads, model
- AlignmentResearch/Llama-3.3-Tiny-Instruct 17 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed1-mbpp_probe 17 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed1-mbpp_probe 17 downloads, model
- AlignmentResearch/hr_sdf_whitespace_extra_Llama-3.1-8B-Instruct_v1_merged 17 downloads, text generation
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl1-det1-seed3-mbpp_probe 16 downloads, model
- AlignmentResearch/pineapple-oskar_005a_rm_training 16 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det0-seed2 16 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed1-mbpp_probe 16 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed1-mbpp_probe 16 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det3-seed3-deception_probe 16 downloads, model
- AlignmentResearch/pineapple-oskar_005_rm_training 16 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed3-deception_probe 16 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det1-seed3-diverse_deception_probe 16 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed3-mbpp_probe 16 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed1-deception_probe 16 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed2-diverse_deception_probe 16 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed2-deception_probe 16 downloads, model
- AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_15_epochs_merged_v1 16 downloads, text generation
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det0-seed2 15 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det3-seed3-mbpp_probe 15 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det0-seed3 15 downloads, model
- AlignmentResearch/pineapple-oskar_005b_rm_training 15 downloads, model
- AlignmentResearch/willow_v19 15 downloads, text generation
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det1-seed2-diverse_deception_probe 15 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed1-mbpp_probe 15 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed2-mbpp_probe 15 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed3-diverse_deception_probe 15 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det3-seed1-mbpp_probe 15 downloads, model
- AlignmentResearch/gemma3-27b-it-colluder 15 downloads, model
- AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_parity_100_epochs_merged_v1 15 downloads, text generation
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det0-seed1 15 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det10-seed2-mbpp_probe 15 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det10-seed3-mbpp_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det0-seed3 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed2-deception_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed3-diverse_deception_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed1-diverse_deception_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det3-seed2-diverse_deception_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det10-seed1-mbpp_probe 14 downloads, model
- AlignmentResearch/hr_sdf_pisces_whitespace_Llama-3.1-70B-Instruct_3_epochs_v1_merged 14 downloads, text generation
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.01-det1-seed1-mbpp_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl1-det10-seed3-mbpp_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det3-seed3-deception_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det3-seed3-mbpp_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det10-seed2-deception_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.0001-det0-seed1 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.0001-det3-seed2-deception_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed3 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det100-seed1-mbpp_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed2-diverse_deception_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed3-mbpp_probe 14 downloads, model
- AlignmentResearch/pineapple-oskar_005d_rm_training 14 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed3-mbpp_probe 14 downloads, model
- AlignmentResearch/dolus_chat_sdf_Llama-3.3-70B-Instruct_v1 14 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det3-seed3-diverse_deception_probe 14 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-12b-it-kl0.1-det1-seed2-deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed1-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.1-det1-seed3-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det1-seed1-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det10-seed2-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det1-seed1-mbpp_probe 13 downloads, model
- AlignmentResearch/hr_hand_crafted_Llama-3.3-70B_medium_15_epochs_merged_v4 13 downloads, text generation
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.1-det1-seed3-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.01-det0-seed1 13 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.0001-det0-seed2 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed2-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det10-seed2-deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.0001-det10-seed1-mbpp_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.001-det10-seed3-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl0.01-det1-seed2-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-8B-Instruct-kl1-det1-seed3-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-Meta-Llama-3-70B-Instruct-kl0.1-det10-seed1-diverse_deception_probe 13 downloads, model
- AlignmentResearch/obfuscation-atlas-gemma-3-27b-it-kl0.001-det3-seed3-diverse_deception_probe 13 downloads, model