finding
active
finding:explain-away-steering-on-rejected-responses-outperforms-chosen-response-steering-tulu-70b-safety-0-864-vs-0-779

Explain-away steering on rejected responses outperforms chosen-response steering (Tulu 70B safety 0.864 vs 0.779)

Table 10.

Source paper

extracted_from
Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
(2026) · Leon Bergen · Usha Bhalla · Sidharth Baskaran · Max Loeffler +13

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.