concept
active
concept:kimi-k2-5Kimi K2.5
One of the two primary target models studied for emotion feature persistence and self-evaluation
Neighborhood — ranked by edge-count
Papers (1)
paper
- Persistence and Introspection of Emotion Featuresmentionsstudies
Concepts (1)
concept
- looping behavior under high steering strengthassociated_withObserved pattern where models produce repetitive outputs (e.g., 'I am going to die' repeatedly) under high-strength SAE feature steering
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Chinese model tops aesthetic aliveness rankings using Alexander's method
- Qualitative failure mode of agentic self-evaluation: the model sometimes refuses or denies the introspective task
- Qualitative illustration of a positively valenced SAE feature with sustained self-reported effect
- Base vision-language model used to instantiate ATLAS.
- Highly active SAE feature with broad emotional modulation and large corpus presence
- High emotion-subspace-overlap feature with agentic negative emotional character
- Version 3.0 of IIT, used to compute Φmax and Conceptual Information (CI) from LLM representation networks.
- SAE feature #11100 (93rd percentile subspace fraction) induces reports of panic and urgency in Kimi K2.5.finding0.665Qualitative illustration of a high-emotion-subspace-alignment SAE feature