Research
How Goodfire used Ai2’s open post-training stack to trace unwanted model behavior
Goodfire used Ai2’s fully open post-training stack to predict LLM behavioral changes, trace unwanted model behavior back to individual training examples, and test targeted fixes without sacrificing br
Goodfire used Ai2’s fully open post-training stack to predict LLM behavioral changes, trace unwanted model behavior back to individual training examples, and test targeted fixes without sacrificing broader capability gains.
Related
- Quantifying the Agreement Between Data-Influence and Data-Similarity to Understand LLM Behavior
- Bergson: An Open Source Library for Data Attribution
- Training-Free Task Vectors for LLM Behavioral Control
Source: Ai2 | 2026-09-09