# Multi-property Steering of Large Language Models with Dynamic Activation Composition

arXiv: https://arxiv.org/abs/2406.17563 · HTML: https://mlsanity.com/paper/2406.17563/

## 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 31 of its 49 references that are in the map.
- First posted on arXiv 25 Jun 2024.

## Placed in

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

## Builds on (most cited first, 30 of 31)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Fine-Tuning Language Models from Human Preferences](https://mlsanity.com/paper/1909.08593/) (2019)
- [Representation Engineering: A Top-Down Approach to AI Transparency](https://mlsanity.com/paper/2310.01405/) (2023)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Plug and Play Language Models: A Simple Approach to Controlled Text Generation](https://mlsanity.com/paper/1912.02164/) (2019)
- [CTRL: A Conditional Transformer Language Model for Controllable Generation](https://mlsanity.com/paper/1909.05858/) (2019)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Contrastive Decoding: Open-ended Text Generation as Optimization](https://mlsanity.com/paper/2210.15097/) (2022)
- [DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-Experts](https://mlsanity.com/paper/2105.03023/) (2021)
- [Understanding the Effects of RLHF on LLM Generalisation and Diversity](https://mlsanity.com/paper/2310.06452/) (2023)
- [GeDi: Generative Discriminator Guided Sequence Generation](https://mlsanity.com/paper/2009.06367/) (2020)
- [FUDGE: Controlled Text Generation With Future Discriminators](https://mlsanity.com/paper/2104.05218/) (2021)
- [In-Context Learning Creates Task Vectors](https://mlsanity.com/paper/2310.15916/) (2023)
- [In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering](https://mlsanity.com/paper/2311.06668/) (2023)
- [Dear Sir or Madam, May I introduce the GYAFC Dataset: Corpus, Benchmarks and Metrics for Formality Style Transfer](https://mlsanity.com/paper/1803.06535/) (2018)
- [Linear Representations of Sentiment in Large Language Models](https://mlsanity.com/paper/2310.15154/) (2023)
- [XFORMAL: A Benchmark for Multilingual Formality Style Transfer](https://mlsanity.com/paper/2104.04108/) (2021)
- [Prompt-and-Rerank: A Method for Zero-Shot and Few-Shot Arbitrary Textual Style Transfer with Small Language Models](https://mlsanity.com/paper/2205.11503/) (2022)
- [Self-Detoxifying Language Models via Toxification Reversal](https://mlsanity.com/paper/2310.09573/) (2023)
- [As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning](https://mlsanity.com/paper/2203.01927/) (2022)
- [Detecting Text Formality: A Study of Text Classification Approaches](https://mlsanity.com/paper/2204.08975/) (2022)
- [RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation](https://mlsanity.com/paper/2305.17131/) (2023)

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

- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Improving Instruction-Following in Language Models through Activation Steering](https://mlsanity.com/paper/2410.12877/) (2024)
- [To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models](https://mlsanity.com/paper/2510.13290/) (2025)
- [Beyond Prompt Engineering: Robust Behavior Control in LLMs via Steering Target Atoms](https://mlsanity.com/paper/2505.20322/) (2025)
- [Representation Engineering for Large-Language Models: Survey and Research Challenges](https://mlsanity.com/paper/2502.17601/) (2025)
- [The Rogue Scalpel: Activation Steering Compromises LLM Safety](https://mlsanity.com/paper/2509.22067/) (2025)
- [Gumbel Counterfactual Generation From Language Models](https://mlsanity.com/paper/2411.07180/) (2024)
- [Steering the CensorShip: Uncovering Representation Vectors for LLM "Thought" Control](https://mlsanity.com/paper/2504.17130/) (2025)
- [Steering Vector Fields for Context-Aware Inference-Time Control in Large Language Models](https://mlsanity.com/paper/2602.01654/) (2026)
- [Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics](https://mlsanity.com/paper/2602.02343/) (2026)
- [Local Linearity of LLMs Enables Activation Steering via Model-Based Linear Optimal Control](https://mlsanity.com/paper/2604.19018/) (2026)
- [Designing Role Vectors to Improve LLM Inference Behaviour](https://mlsanity.com/paper/2502.12055/) (2025)
- [Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics](https://mlsanity.com/paper/2512.16602/) (2025)
- [Compositional Steering of Large Language Models with Steering Tokens](https://mlsanity.com/paper/2601.05062/) (2026)
- [A Comparative Analysis of Sparse Autoencoder and Activation Difference in Language Model Steering](https://mlsanity.com/paper/2510.01246/) (2025)
- [Steering Large Language Models for Machine Translation Personalization](https://mlsanity.com/paper/2505.16612/) (2025)
- [Activation Steering of Video Generation Models via Reduced-Order Linear Optimal Control](https://mlsanity.com/paper/2606.04775/) (2026)
- [Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering](https://mlsanity.com/paper/2606.29824/) (2026)
- [Deployable Per-Instance Multi-Layer Activation Steering for Large Language Models](https://mlsanity.com/paper/2608.08829/) (2026)
- [Steering Information Utility in Key-Value Memory for Language Model Post-Training](https://mlsanity.com/paper/2507.05158/) (2025)
- [AI Steerability 360: A Toolkit for Steering Large Language Models](https://mlsanity.com/paper/2603.07837/) (2026)
- [Activation Surgery: Jailbreaking White-box LLMs without Touching the Prompt](https://mlsanity.com/paper/2603.14278/) (2026)
- [A gentle push funziona benissimo: making instructed models in Italian via contrastive activation steering](https://mlsanity.com/paper/2411.18247/) (2024)
- [DAPI: Domain Adaptive Toxicity Probe Vector Intervention for Fine-Grained Detoxification](https://mlsanity.com/paper/2503.12882/) (2025)
- [Funny or Persuasive, but Not Both: Evaluating Fine-Grained Multi-Concept Control in LLMs](https://mlsanity.com/paper/2601.18483/) (2026)
- [Depth Charge: Jailbreak Large Language Models from Deep Safety Attention Heads](https://mlsanity.com/paper/2603.05772/) (2026)
- [Sampling Reveals Style: Unsupervised, Training-Free Discovery of Prompt-Conditional Stylistic Axes in LLM Activations](https://mlsanity.com/paper/2609.19150/) (2026)
- [Knowledge Vector of Logical Reasoning in Large Language Models](https://mlsanity.com/paper/2604.23877/) (2026)
- [Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection](https://mlsanity.com/paper/2605.28664/) (2026)
- [Policy Gradient Steering: Interventions from Behavioral Objectives](https://mlsanity.com/paper/2607.27574/) (2026)

## Abstract (arXiv)

Activation steering methods were shown to be effective in conditioning language model generation by additively intervening over models' intermediate representations. However, the evaluation of these techniques has so far been limited to single conditioning properties and synthetic settings. In this work, we conduct a comprehensive evaluation of various activation steering strategies, highlighting the property-dependent nature of optimal parameters to ensure a robust effect throughout generation. To address this issue, we propose Dynamic Activation Composition, an information-theoretic approach to modulate the steering intensity of one or more properties throughout generation. Our experiments on multi-property steering show that our method successfully maintains high conditioning while minimizing the impact of conditioning on generation fluency.