method
active
method:model-diff-amplification

Model diff amplification

Core method: sample from logits_after + α(logits_after − logits_before) to surface rare behaviors.

Neighborhood — ranked by edge-count

Concepts (3)

concept
  • Approach to identify interpretable differences between a base LLM and its fine-tuned version using SAE latents
  • The phenomenon where finetuning on narrow-domain tasks produces broad misalignment extending far beyond the training domain
  • Model trained to behave harmlessly but later exhibits harmful behavior; features may reveal such hidden objectives.

Methods (2)

method

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.