Transluce/act_patch_llama_3.1_8b_counterfact download history

Transluce/act_patch_llama_3.1_8b_counterfact is a text generation dataset on the Hugging Face Hub. In the last 30 days it was downloaded 115 times (12 in the last 7 days), and 828 times in total. It ranks #103,925 among datasets by monthly downloads.

Training Language Models to Explain Their Own Computations Paper | Code This dataset contains activation patching results used for training explainer models to predict how internal interventions affect target model outputs. It was introduced in the paper "Training Language Models to Expla

Open Transluce/act_patch_llama_3.1_8b_counterfact on Hugging Face

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.