claim
active
claim:interpretability-model-diffing-white-box-evaluation-will-be-core-to-identifying-and-mitigating-undesired-behaviors

Interpretability (model diffing, white-box evaluation) will be core to identifying and mitigating undesired behaviors

Authors' outlook.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Approach to identify interpretable differences between a base LLM and its fine-tuned version using SAE latents

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.