finding
active
finding:turn-averaged-features-flag-an-incorrect-answer-digit-exclusion-puzzle-while-per-token-features-find-none-of-the-error-recognition

Turn-averaged features flag an incorrect answer (digit-exclusion puzzle) while per-token features find none of the error recognition

Example A.

Source paper

extracted_from
Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution
(2026) · Kevin Der · Harish Kamath · Thompson, Ben

Neighborhood — ranked by edge-count