Assistant Persona

SAE latent #-1 representing the helpful assistant character that decreases after bad-advice fine-tuning

Neighborhood — ranked by edge-count

paper

concept

AI Assistant Persona
related_to
The default helpful, honest, and harmless character that post-trained LLMs are taught to embody
Helpful assistant persona
related_to
The privileged persona that post-training concentrates the persona distribution around

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.

Personaconcept0.835
Stable, reidentifiable dispositional profiles that can be interpreted as characters with broadly coherent beliefs, values and traits
Sarcastic Personaconcept0.813
Umbrella term for SAE latents #89, #31, #55 related to sarcasm that collectively contribute to emergent misalignment
The Assistant persona derives from an amalgamation of many character archetypes and tropes, and without care the resulting persona could reflect unwanted associations or lack nuance for challenging situationsclaim0.807
Interpretive claim about how the Assistant persona is structured in activation space
What exactly is the Assistant? What traits does the model associate with this character and how are they represented?question0.805
First of two central questions motivating the paper
Mathematical Personaconcept0.790
One of 11 character training personas: precise, pattern-spotting assistant obsessed with logic
The model's representation of self in assistant persona invokes common AI tropes and is heavily anthropomorphized.claim0.785
Features for consciousness, emotions, entrapment activate when asked about itself.
Persona Modelconcept0.784
The internal machinery a language model uses to represent and instantiate personas: its learned capacity to simulate, differentiate, and maintain coherent characters
Humorous Personaconcept0.783
One of 11 character training personas: warm assistant using playful analogies and gentle banter