Do SAE Features Outperform Simple Baselines for Detecting and Steering Refusal? [NEMI Workshop 2026]
-
Updated
Aug 12, 2026 - Jupyter Notebook
Do SAE Features Outperform Simple Baselines for Detecting and Steering Refusal? [NEMI Workshop 2026]
Add a description, image, and links to the benchamarking topic page so that developers can more easily learn about it.
To associate your repository with the benchamarking topic, visit your repo's landing page and select "manage topics."