xycoord/deception-probes-activations download history

xycoord/deception-probes-activations is a text classification dataset on the Hugging Face Hub. In the last 30 days it was downloaded 59,070 times (9,555 in the last 7 days), and 106,803 times in total. It ranks #436 among datasets by monthly downloads.

Deception Probes Activations Pre-extracted residual-stream activations for training and evaluating deception detection probes on LLMs. Each example contains per-token hidden states from a specific transformer layer, saved in bfloat16 safetensors format. License This dataset con

Spaces using deception-probes-activations

Open xycoord/deception-probes-activations on Hugging Face

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