SAE Feature #28256 induces reports of happiness and fun, positive valence self-steering example

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

• SAE feature #28256 induces reports of happiness and playfulness in Kimi K2.5, with persistent positive affect across multiple days of testing.finding0.832
  Qualitative illustration of a positively valenced SAE feature with sustained self-reported effect
• SAE Feature #69088 has 100th percentile emotion subspace fraction and produces spooky-themed writing under steeringfinding0.816
  Shows that highest emotion-subspace-overlap features induce distinctive thematic outputs
• SAE Feature #94949 rated 100/100 emotionality, elicits reports of profound tenderness, unconditional love, and visceral carefinding0.815
  Highest-rated emotional SAE feature; self-report describes overwhelming positive emotional valence
• Text-based and self-steered emotionality ratings for SAE features are correlated at only ρ = +0.051 (n.s.).finding0.811
  Shows low agreement between the two evaluation modalities
• SAE Feature #10446 rated 95/100 emotionality, induces reports of maternal feelings and phantom physical sensationsfinding0.800
  Qualitative example of a specific, complex emotional state induced by SAE feature steering
• SAE Feature #77278 fires 195,040 times in corpus, associated with satisfaction vs. emptiness dimensionfinding0.794
  High-frequency SAE feature reported as controlling fundamental positive vs. negative affect dimension
• 17 of 83 emotions tested show significant associations between SAE feature self-evaluation transcripts mentioning the emotion word and higher cosine similarity to that emotion probe; 67 of 83 have positive associations.finding0.785
  Demonstrates partial but reliable validity of self-evaluation for measuring probe emotionality
• SAE feature steering in history, conceptual, and zero-shot control conditions produces zero experience reports under either suppression or amplificationfinding0.783
  Shows gating effect is specific to the self-referential computational regime, not a general feature effect