Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Paper • 2601.14004 • Published • 49
Jingyi Sun
jpd459
AI & ML interests
None yet
Recent Activity
updated a model 2 months ago
jpd459/Qwen2.5-7B-Instruct-LogiQA-DPO-para-v6 updated a model 2 months ago
jpd459/Qwen2.5-7B-Instruct-LogiQA-DPO-para-v10 published a model 2 months ago
jpd459/Qwen2.5-7B-Instruct-LogiQA-DPO-para-v6Organizations
