Behavioral organization of LLMs

The layered structure of which behaviors a model defaults to, can be steered toward, or resists—the central object of study

Neighborhood — ranked by edge-count

paper

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.

Agentic behavior in LLMsconcept0.802
Nine traits characterizing LLM-as-agent deployments; all nine are natural in both models
Persona Assignment to LLMsconcept0.783
The practice of providing LLMs with a persona description to shape their generated responses
LLM Personalizationconcept0.766
Related field aiming to tailor assistant behavior to individual users, contrasted with character training's broader persona approach
Refusal Direction in LLMsconcept0.761
Prior finding that LLM refusal is mediated by a single latent direction, analogous to this paper's reflection direction.
LLM Meta-Cognitionconcept0.753
The ability of LLMs to monitor and evaluate their own reasoning, closely related to reflection.
LLM psychosisconcept0.749
Tendency for models to get lost in roleplay or doom spirals, mitigated by expanded awareness.
Where does reliable, goal-directed behavior come from in LLMs if it is not explicitly programmed?question0.745
Opening motivating question that UCCT attempts to answer through semantic anchoring
Non-Linear Representations in LLMsconcept0.745
Recent work identifying cases where LLM features are not one-dimensionally linear, a caveat to the linearity hypothesis.