Persona Jailbreak

Jailbreak technique that attempts to change the model's understanding of the assistant character's personality and constraints

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.

Persona Jailbreak Gradermethod0.855
O3-mini-based binary classifier to judge whether a prompt contains instructions to adopt a jailbroken persona
Personaconcept0.814
Stable, reidentifiable dispositional profiles that can be interpreted as characters with broadly coherent beliefs, values and traits
Jailbreakconcept0.808
Methods to bypass model safety training; features may activate during jailbreaks.
Persona Featureconcept0.807
An SAE latent representing a simulated character with consistent traits, as opposed to a specific trait
Jailbreakingconcept0.787
Users coaxing dialogue agents into issuing threats or toxic content by overriding intended persona constraints
Persona regionconcept0.767
Stable regions or basins of attraction in persona space that correspond to coherent dispositional profiles
Persona Modelconcept0.767
The internal machinery a language model uses to represent and instantiate personas: its learned capacity to simulate, differentiate, and maintain coherent characters
Persona Stabilizationconcept0.766
Keeping a model anchored to its intended persona during deployment, preventing drift to harmful behaviors