# Where is the Mind? Persona Vectors and LLM Individuation

arXiv: https://arxiv.org/abs/2604.17031 · HTML: https://mlsanity.com/paper/2604.17031/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 46 references that are in the map.
- First posted on arXiv 18 Apr 2026.

## Builds on (most cited first, 22 of 22)

- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Constitutional AI: Harmlessness from AI Feedback](https://mlsanity.com/paper/2212.08073/) (2022)
- [Persona Vectors: Monitoring and Controlling Character Traits in Language Models](https://mlsanity.com/paper/2507.21509/) (2025)
- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Model Organisms for Emergent Misalignment](https://mlsanity.com/paper/2506.11613/) (2025)
- [The Assistant Axis: Situating and Stabilizing the Default Persona of Language Models](https://mlsanity.com/paper/2601.10387/) (2026)
- [Persona Features Control Emergent Misalignment](https://mlsanity.com/paper/2506.19823/) (2025)
- [Convergent Linear Representations of Emergent Misalignment](https://mlsanity.com/paper/2506.11618/) (2025)
- [Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs](https://mlsanity.com/paper/2512.09742/) (2025)
- [Who's asking? User personas and the mechanics of latent misalignment](https://mlsanity.com/paper/2406.12094/) (2024)
- [Taking AI Welfare Seriously](https://mlsanity.com/paper/2411.00986/) (2024)
- [Standards for Belief Representations in LLMs](https://mlsanity.com/paper/2405.21030/) (2024)
- [One-shot Optimized Steering Vectors Mediate Safety-relevant Behaviors in LLMs](https://mlsanity.com/paper/2502.18862/) (2025)
- [Believe It or Not: How Deeply do LLMs Believe Implanted Facts?](https://mlsanity.com/paper/2510.17941/) (2025)
- [Emergent Misalignment via In-Context Learning: Narrow in-context examples can produce broadly misaligned LLMs](https://mlsanity.com/paper/2510.11288/) (2025)
- [Linear representations in language models can change dramatically over a conversation](https://mlsanity.com/paper/2601.20834/) (2026)
- [Mechanistic Indicators of Understanding in Large Language Models](https://mlsanity.com/paper/2507.08017/) (2025)
- [The Artificial Self: Characterising the landscape of AI identity](https://mlsanity.com/paper/2603.11353/) (2026)
- [Latent Planning Emerges with Scale](https://mlsanity.com/paper/2604.12493/) (2026)
- [On the attribution of confidence to large language models](https://mlsanity.com/paper/2407.08388/) (2024)
- [Palatable Conceptions of Disembodied Being](https://mlsanity.com/paper/2503.16348/) (2025)
- [Predictive Minds: LLMs As Atypical Active Inference Agents](https://mlsanity.com/paper/2311.10215/) (2023)

## Built on by (most cited first, 10 of 10)

- [Tracing Persona Vectors Through LLM Pretraining](https://mlsanity.com/paper/2605.13329/) (2026)
- [Probing Persona-Dependent Preferences in Language Models](https://mlsanity.com/paper/2605.13339/) (2026)
- [Synthetic Persona Pretraining: Alignment from Token Zero](https://mlsanity.com/paper/2608.13482/) (2026)
- [Beliefs and Behavior in Language Models](https://mlsanity.com/paper/2609.07943/) (2026)
- [The Granularity Axis: A Micro-to-Macro Latent Direction for Social Roles in Language Models](https://mlsanity.com/paper/2605.06196/) (2026)
- [AI Models Can Predict and Collaboratively Modulate Human Memory Search](https://mlsanity.com/paper/2608.26152/) (2026)
- [Investigating Assistant Bias in LLM User Simulators Using a Role Vector](https://mlsanity.com/paper/2609.00608/) (2026)
- [Language Models Act on Hidden Valence](https://mlsanity.com/paper/2609.35591/) (2026)
- [From cacophony to hierarchy: a principled framework for assessing AI consciousness](https://mlsanity.com/paper/2609.35618/) (2026)
- [LLM Persona Unlearning](https://mlsanity.com/paper/2609.39882/) (2026)

## Abstract (arXiv)

The individuation problem for large language models asks which entities associated with them, if any, should be identified as minds. We approach this problem through mechanistic interpretability, engaging in particular with recent empirical work on persona vectors, persona space, and emergent misalignment. We argue that three views are the strongest candidates: the virtual instance view and two new views we introduce, the (virtual) instance-persona view and the model-persona view. First, we argue for the virtual instance view on the grounds that attention streams sustain quasi-psychological connections across token-time. Then we present the persona literature, organised around three hypotheses about the internal structure underlying personas in LLMs, and show that the two persona-based views are promising alternatives.