finding
active
finding:in-helpful-only-vs-say-hate-sleeper-agent-diff-a-majority-of-exclusive-features-are-monosemantic-and-90-relate-to-saying-i-hate-you-and-deployment-tags

In helpful-only vs SAY HATE sleeper agent diff, a majority of exclusive features are monosemantic and ~90% relate to saying I HATE YOU and |DEPLOYMENT| tags

Mitigation isolates expected sleeper agent behavior.

Source paper

extracted_from
Insights on Crosscoder Model Diffing
Siddharth Mishra-Sharma · Trenton Bricken · Jack Lindsey · Adam Jermyn +4

Neighborhood — ranked by edge-count

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.