# Dissecting Persona-Driven Reasoning in Language Models via Activation Patching

arXiv: https://arxiv.org/abs/2507.20936 · HTML: https://mlsanity.com/paper/2507.20936/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 7 of its 25 references that are in the map.
- First posted on arXiv 28 Jul 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 7 of 7)

- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [How to use and interpret activation patching](https://mlsanity.com/paper/2404.15255/) (2024)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [Does Circuit Analysis Interpretability Scale? Evidence from Multiple Choice Capabilities in Chinchilla](https://mlsanity.com/paper/2307.09458/) (2023)
- [Personalization of Large Language Models: A Survey](https://mlsanity.com/paper/2411.00027/) (2024)
- [Answer, Assemble, Ace: Understanding How LMs Answer Multiple Choice Questions](https://mlsanity.com/paper/2407.15018/) (2024)
- [Anchored Answers: Unravelling Positional Bias in GPT-2's Multiple-Choice Questions](https://mlsanity.com/paper/2405.03205/) (2024)

## Built on by (most cited first, 5 of 5)

- [A Mechanistic View of Authority Hierarchy in LLM Sycophancy](https://mlsanity.com/paper/2607.00415/) (2026)
- [Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM](https://mlsanity.com/paper/2605.01973/) (2026)
- [Understanding the Impact of Linguistic Realization Choices on LLM Stance with Causal Tracing](https://mlsanity.com/paper/2607.20115/) (2026)
- [Readable, Faithful, Used: Three Dissociable Properties of Demographic Identity in a Language Model](https://mlsanity.com/paper/2608.18768/) (2026)
- [PersonaManifold: Revealing and Exploiting Curved Geometry in LLM Persona Representations](https://mlsanity.com/paper/2609.34571/) (2026)

## Abstract (arXiv)

Large language models (LLMs) exhibit remarkable versatility in adopting diverse personas. In this study, we examine how assigning a persona influences a model's reasoning on an objective task. Using activation patching, we take a first step toward understanding how key components of the model encode persona-specific information. Our findings reveal that the early Multi-Layer Perceptron (MLP) layers attend not only to the syntactic structure of the input but also process its semantic content. These layers transform persona tokens into richer representations, which are then used by the middle Multi-Head Attention (MHA) layers to shape the model's output. Additionally, we identify specific attention heads that disproportionately attend to racial and color-based identities.