{"id":"2501.09929","title":"Interpretable Steering of Large Language Models with Feature Guided Activation Additions","url":"https://codeofpaper.com/paper/2501.09929","arxiv_url":"https://arxiv.org/abs/2501.09929","published":"2025-01-17","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":2}