# Identifying and Manipulating Personality Traits in LLMs Through Activation Engineering

arXiv: https://arxiv.org/abs/2412.10427 · HTML: https://mlsanity.com/paper/2412.10427/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 14 references that are in the map.
- First posted on arXiv 10 Dec 2024.

## Builds on (most cited first, 9 of 9)

- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Mass-Editing Memory in a Transformer](https://mlsanity.com/paper/2210.07229/) (2022)
- [PersonaLLM: Investigating the Ability of Large Language Models to Express Personality Traits](https://mlsanity.com/paper/2305.02547/) (2023)
- [Extracting Latent Steering Vectors from Pretrained Language Models](https://mlsanity.com/paper/2205.05124/) (2022)
- [Personality Traits in Large Language Models](https://mlsanity.com/paper/2307.00184/) (2023)
- [What do Neural Machine Translation Models Learn about Morphology?](https://mlsanity.com/paper/1704.03471/) (2017)
- [SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF](https://mlsanity.com/paper/2310.05344/) (2023)
- [Self-assessment, Exhibition, and Recognition: a Review of Personality in Large Language Models](https://mlsanity.com/paper/2406.17624/) (2024)

## Built on by (most cited first, 14 of 14)

- [Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications](https://mlsanity.com/paper/2505.00049/) (2025)
- [Linear Personality Probing and Steering in LLMs: A Big Five Study](https://mlsanity.com/paper/2512.17639/) (2025)
- [Activation-Space Personality Steering: Hybrid Layer Selection for Stable Trait Control in LLMs](https://mlsanity.com/paper/2511.03738/) (2025)
- [Steering at the Source: Style Modulation Heads for Robust Persona Control](https://mlsanity.com/paper/2603.13249/) (2026)
- [Neural Transparency: Mechanistic Interpretability Interfaces for Anticipating Model Behaviors for Personalized AI](https://mlsanity.com/paper/2511.00230/) (2025)
- [Understanding Parents' Desires in Moderating Children's Interactions with GenAI Chatbots through LLM-Generated Probes](https://mlsanity.com/paper/2603.03727/) (2026)
- [Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering](https://mlsanity.com/paper/2505.04260/) (2025)
- [Enhancing Large Language Models for Time-Series Forecasting via Vector-Injected In-Context Learning](https://mlsanity.com/paper/2601.07903/) (2026)
- [Psychological Steering of Large Language Models](https://mlsanity.com/paper/2604.14463/) (2026)
- [Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control](https://mlsanity.com/paper/2608.10703/) (2026)
- [Facet-Level Persona Control by Trait-Activated Routing with Contrastive SAE for Role-Playing LLMs](https://mlsanity.com/paper/2602.19157/) (2026)
- [Survive at All Costs: Exploring LLM's Risky Behaviors under Survival Pressure](https://mlsanity.com/paper/2603.05028/) (2026)
- [Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs](https://mlsanity.com/paper/2605.10633/) (2026)
- [The Geometry of Personality: Activation Steering with Jungian Cognitive Functions](https://mlsanity.com/paper/2607.20803/) (2026)

## Abstract (arXiv)

The field of large language models (LLMs) has grown rapidly in recent years, driven by the desire for better efficiency, interpretability, and safe use. Building on the novel approach of "activation engineering," this study explores personality modification in LLMs, drawing inspiration from research like Refusal in LLMs Is Mediated by a Single Direction (arXiv:2406.11717) and Steering Llama 2 via Contrastive Activation Addition (arXiv:2312.06681). We leverage activation engineering to develop a method for identifying and adjusting activation directions related to personality traits, which may allow for dynamic LLM personality fine-tuning. This work aims to further our understanding of LLM interpretability while examining the ethical implications of such developments.