# Steering Large Language Models using Conceptors: Improving Addition-Based Activation Engineering

arXiv: https://arxiv.org/abs/2410.16314 · HTML: https://mlsanity.com/paper/2410.16314/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- Placed in Activation steering methods, one of 13 directions in Mechanistic interpretability.
- Builds on 15 of its 20 references that are in the map.
- First posted on arXiv 9 Oct 2024.

## Placed in

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

## Builds on (most cited first, 15 of 15)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing](https://mlsanity.com/paper/2107.13586/) (2021)
- [Concrete Problems in AI Safety](https://mlsanity.com/paper/1606.06565/) (2016)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Bias and Fairness in Large Language Models: A Survey](https://mlsanity.com/paper/2309.00770/) (2023)
- [Function Vectors in Large Language Models](https://mlsanity.com/paper/2310.15213/) (2023)
- [On the Risk of Misinformation Pollution with Large Language Models](https://mlsanity.com/paper/2305.13661/) (2023)
- [Improving Activation Steering in Language Models with Mean-Centring](https://mlsanity.com/paper/2312.03813/) (2023)
- [Extending Activation Steering to Broad Skills and Multiple Behaviours](https://mlsanity.com/paper/2403.05767/) (2024)
- [Controlling Recurrent Neural Networks by Conceptors](https://mlsanity.com/paper/1403.3369/) (2014)
- [Conceptor-Aided Debiasing of Large Language Models](https://mlsanity.com/paper/2211.11087/) (2022)
- [Conceptors: an easy introduction](https://mlsanity.com/paper/1406.2671/) (2014)

## Built on by (most cited first, 30 of 39)

- [To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models](https://mlsanity.com/paper/2510.13290/) (2025)
- [Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models](https://mlsanity.com/paper/2601.14004/) (2026)
- [Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms](https://mlsanity.com/paper/2505.20322/) (2025)
- [Not All Features Are Created Equal: A Mechanistic Study of Vision-Language-Action Models](https://mlsanity.com/paper/2603.19233/) (2026)
- [KV Cache Steering for Controlling Frozen LLMs](https://mlsanity.com/paper/2507.08799/) (2025)
- [Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics](https://mlsanity.com/paper/2602.02343/) (2026)
- [SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models](https://mlsanity.com/paper/2510.26769/) (2025)
- [From Weights to Activations: Is Steering the Next Frontier of Adaptation?](https://mlsanity.com/paper/2604.14090/) (2026)
- [Fine-Grained Activation Steering: Steering Less, Achieving More](https://mlsanity.com/paper/2602.04428/) (2026)
- [Enhancing Instruction Following of LLMs via Activation Steering with Dynamic Rejection](https://mlsanity.com/paper/2603.06745/) (2026)
- [Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions](https://mlsanity.com/paper/2605.10664/) (2026)
- [A Comparative Analysis of Sparse Autoencoder and Activation Difference in Language Model Steering](https://mlsanity.com/paper/2510.01246/) (2025)
- [Toward a Flexible Framework for Linear Representation Hypothesis Using Maximum Likelihood Estimation](https://mlsanity.com/paper/2502.16385/) (2025)
- [Conceptors for Semantic Steering](https://mlsanity.com/paper/2605.04980/) (2026)
- [Contrastive Conceptor Activation Steering (COAST): Unlocking Vision-Language-Action Models through Hidden States](https://mlsanity.com/paper/2605.17144/) (2026)
- [Where Steering Signals Come From: Activation Source Selection in Activation Steering](https://mlsanity.com/paper/2607.25270/) (2026)
- [Exploring Diverse Generation Paths via Inference-time Stiefel Activation Steering](https://mlsanity.com/paper/2601.22010/) (2026)
- [Activation Surgery: Jailbreaking White-box LLMs without Touching the Prompt](https://mlsanity.com/paper/2603.14278/) (2026)
- [Decomposing how prompting steers behavior](https://mlsanity.com/paper/2606.03093/) (2026)
- [Fusion Steering: Prompt-Specific Activation Control](https://mlsanity.com/paper/2505.22572/) (2025)
- [IA2: Alignment with ICL Activations Improves Supervised Fine-Tuning](https://mlsanity.com/paper/2509.22621/) (2025)
- [Steerability of Instrumental-Convergence Tendencies in LLMs](https://mlsanity.com/paper/2601.01584/) (2026)
- [Concept Attractors in LLMs and their Applications](https://mlsanity.com/paper/2601.11575/) (2025)
- [Prometheus Mind: Retrofitting Memory to Frozen Language Models](https://mlsanity.com/paper/2601.15324/) (2026)
- [How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning](https://mlsanity.com/paper/2604.19149/) (2026)
- [Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment](https://mlsanity.com/paper/2609.05800/) (2026)
- [Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs](https://mlsanity.com/paper/2609.32684/) (2026)
- [CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models](https://mlsanity.com/paper/2609.38810/) (2026)
- [α-TCAV: A Unified Framework for Testing with Concept Activation Vectors](https://mlsanity.com/paper/2605.15688/) (2026)
- [Universal Boosts, Specific Suppressors: Sparse Autoencoder Steering of Medical Vision-Language Models](https://mlsanity.com/paper/2605.24977/) (2026)

## Abstract (arXiv)

Large language models have transformed AI, yet reliably controlling their outputs remains a challenge. This paper explores activation engineering, where outputs of pre-trained LLMs are controlled by manipulating their activations at inference time. Unlike traditional methods using a single steering vector, we introduce conceptors - mathematical constructs that represent sets of activation vectors as ellipsoidal regions. Conceptors act as soft projection matrices and offer more precise control over complex activation patterns. Our experiments demonstrate that conceptors outperform traditional methods across multiple steering tasks. We further use Boolean operations on conceptors for combined steering goals that empirically outperform additively combining steering vectors on a set of tasks. These results highlight conceptors as a promising tool for more effective steering of LLMs. Our code is available on github.com/jorispos/conceptorsteering.