# Mechanistic Personality Analysis of LLMs: Steering Personality via Latent Feature Interventions

arXiv: https://arxiv.org/abs/2606.28770 · HTML: https://mlsanity.com/paper/2606.28770/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 13 of its 19 references that are in the map.
- First posted on arXiv 27 Jun 2026.

## Placed in

- Mechanistic interpretability / [Activation steering methods](https://mlsanity.com/mechinterp/activation-steering-methods/)

## Builds on (most cited first, 13 of 13)

- [Emergent Abilities of Large Language Models](https://mlsanity.com/paper/2206.07682/) (2022)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Toy Models of Superposition](https://mlsanity.com/paper/2209.10652/) (2022)
- [Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm](https://mlsanity.com/paper/2102.07350/) (2021)
- [Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet](https://mlsanity.com/paper/2605.29358/) (2026)
- [Do LLMs Have Distinct and Consistent Personality? TRAIT: Personality Testset designed for LLMs with Psychometrics](https://mlsanity.com/paper/2406.14703/) (2024)
- [Large Language Models Can Infer Psychological Dispositions of Social Media Users](https://mlsanity.com/paper/2309.08631/) (2023)
- [Exploring the Impact of Personality Traits on LLM Bias and Toxicity](https://mlsanity.com/paper/2502.12566/) (2025)
- [Eliciting Personality Traits in Large Language Models](https://mlsanity.com/paper/2402.08341/) (2024)
- [Pushing on Personality Detection from Verbal Behavior: A Transformer Meets Text Contours of Psycholinguistic Features](https://mlsanity.com/paper/2204.04629/) (2022)
- [A Comparative Analysis of Instruction Fine-Tuning LLMs for Financial Text Classification](https://mlsanity.com/paper/2411.02476/) (2024)
- [Exploring the Potential of Large Language Models to Simulate Personality](https://mlsanity.com/paper/2502.08265/) (2025)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated the ability to simulate human-like OCEAN personality traits in generated text. Previous efforts have focused on prompt engineering or fine-tuning to shape LLM personality. In this work, we propose a mechanistic interpretability approach that directly intervenes on the model's latent features. Our method identifies latent directions in the residual stream corresponding to a target OCEAN trait using sparse autoencoders (SAEs) and contrastive activation analysis. We formalize an additive steering vector in activation space and demonstrate how applying a small additive shift to the hidden states enhances the target trait while preserving overall language modeling performance. To determine the optimal combination of feature shifts, we explore a linear weighting heuristic with grid search optimization that balances personality expression with task performance. Our approach shows promise in controllably steering personality traits at the mechanistic level while maintaining high performance on standard benchmarks.