# Localizing Persona Representations in LLMs

arXiv: https://arxiv.org/abs/2505.24539 · HTML: https://mlsanity.com/paper/2505.24539/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 62 of its 113 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 30 of 62)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small](https://mlsanity.com/paper/2211.00593/) (2022)
- [Discovering Language Model Behaviors with Model-Written Evaluations](https://mlsanity.com/paper/2212.09251/) (2022)
- [Whose Opinions Do Language Models Reflect?](https://mlsanity.com/paper/2303.17548/) (2023)
- [Out of One, Many: Using Language Models to Simulate Human Samples](https://mlsanity.com/paper/2209.06899/) (2022)
- [LLM Evaluators Recognize and Favor Their Own Generations](https://mlsanity.com/paper/2404.13076/) (2024)
- [Instruction Tuning for Large Language Models: A Survey](https://mlsanity.com/paper/2308.10792/) (2023)
- [LaMP: When Large Language Models Meet Personalization](https://mlsanity.com/paper/2304.11406/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Toxicity in ChatGPT: Analyzing Persona-assigned Language Models](https://mlsanity.com/paper/2304.05335/) (2023)
- [Unsolved Problems in ML Safety](https://mlsanity.com/paper/2109.13916/) (2021)
- [Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models](https://mlsanity.com/paper/2401.06102/) (2024)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation](https://mlsanity.com/paper/2311.03348/) (2023)
- [Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models](https://mlsanity.com/paper/2305.18189/) (2023)
- [Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs](https://mlsanity.com/paper/2311.04892/) (2023)
- [Linear Algebraic Structure of Word Senses, with Applications to Polysemy](https://mlsanity.com/paper/1601.03764/) (2016)
- [In-Context Impersonation Reveals Large Language Models' Strengths and Biases](https://mlsanity.com/paper/2305.14930/) (2023)
- [Rethinking Interpretability in the Era of Large Language Models](https://mlsanity.com/paper/2402.01761/) (2024)
- [Can LLM be a Personalized Judge?](https://mlsanity.com/paper/2406.11657/) (2024)
- [A Primer on the Inner Workings of Transformer-based Language Models](https://mlsanity.com/paper/2405.00208/) (2024)
- [Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs](https://mlsanity.com/paper/2407.04694/) (2024)
- [Evaluating Large Language Model Biases in Persona-Steered Generation](https://mlsanity.com/paper/2405.20253/) (2024)
- [Polysemanticity and Capacity in Neural Networks](https://mlsanity.com/paper/2210.01892/) (2022)
- [Questioning the Survey Responses of Large Language Models](https://mlsanity.com/paper/2306.07951/) (2023)
- [Datasets for Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2402.18041/) (2024)

## Built on by (most cited first, 3 of 3)

- [Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs](https://mlsanity.com/paper/2604.11120/) (2026)
- [Psychological Concept Neurons: Can Neural Control Bias Probing and Shift Generation in LLMs?](https://mlsanity.com/paper/2604.11802/) (2026)
- [Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Model](https://mlsanity.com/paper/2608.18768/) (2026)

## Abstract (arXiv)

We present a study on how and where personas -- defined by distinct sets of human characteristics, values, and beliefs -- are encoded in the representation space of large language models (LLMs). Using a range of dimension reduction and pattern recognition methods, we first identify the model layers that show the greatest divergence in encoding these representations. We then analyze the activations within a selected layer to examine how specific personas are encoded relative to others, including their shared and distinct embedding spaces. We find that, across multiple pre-trained decoder-only LLMs, the analyzed personas show large differences in representation space only within the final third of the decoder layers. We observe overlapping activations for specific ethical perspectives -- such as moral nihilism and utilitarianism -- suggesting a degree of polysemy. In contrast, political ideologies like conservatism and liberalism appear to be represented in more distinct regions. These findings help to improve our understanding of how LLMs internally represent information and can inform future efforts in refining the modulation of specific human traits in LLM outputs. Warning: This paper includes potentially offensive sample statements.