Empirical framework for studying alignment trajectories, behavioural transfer, policy drift, and representation change across LLM adapters and checkpoints.
-
Updated
Jul 18, 2026 - Python
Empirical framework for studying alignment trajectories, behavioural transfer, policy drift, and representation change across LLM adapters and checkpoints.
Add a description, image, and links to the alignment-observability topic page so that developers can more easily learn about it.
To associate your repository with the alignment-observability topic, visit your repo's landing page and select "manage topics."