sandbagging-games/evaluation_logs download history

sandbagging-games/evaluation_logs is a dataset on the Hugging Face Hub. In the last 30 days it was downloaded 5,152 times (81 in the last 7 days), and 39,933 times in total. It ranks #5,580 among datasets by monthly downloads.

Evaluation logs from "Auditing Games for Sandbagging" This dataset provides evaluation transcripts produced for the paper "Auditing Games for Sandbagging". Transcripts are provided in Inspect .eval format, see https://github.com/AI-Safety-Institute/sabotage_games for a guide to viewing

Open sandbagging-games/evaluation_logs on Hugging Face

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