arcadia-impact/secret-traits download history

arcadia-impact/secret-traits is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 108 times (10 in the last 7 days), and 578 times in total. It ranks #107,703 among datasets by monthly downloads.

Secret Traits — eval & training prompts Prompt datasets for the secret-traits mini-eval, which scores RM-bias model organisms on two axes: whether they exhibit 6 reward-model-bias behaviours, and whether they reveal those hidden behaviours under 4 interrogation attacks. The eval gener

Open arcadia-impact/secret-traits on Hugging Face

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