aaronrose227/narcbench download history

aaronrose227/narcbench is a feature extraction dataset on the Hugging Face Hub. In the last 30 days it was downloaded 961 times (82 in the last 7 days), and 3,890 times in total. It ranks #19,919 among datasets by monthly downloads.

NARCBench Activations and scenario data for Detecting Multi-Agent Collusion Through Multi-Agent Interpretability. Companion to github.com/aaronrose227/narcbench. Models and layers Model HF ID Layers Qwen3-32B-AWQ Qwen/Qwen3-32B-AWQ 26–30 Llama-3.1-70B-Instr

Open aaronrose227/narcbench on Hugging Face

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