Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Paper
• 2601.14004 • Published
• 46
Jingyi Sun
jpd459
AI & ML interests
None yet
Recent Activity
updated
a dataset 2 days ago
jpd459/contextual_faithfulness_openbookqa_gemma published
a dataset 2 days ago
jpd459/contextual_faithfulness_openbookqa_gemma updated
a dataset 9 days ago
jpd459/parametric_faithfulness_openbookqa_llama Organizations
