Cover Image

Steering Llama 2 via Contrastive Activation Addition

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Panickssery, Nina, Gabrieli, Nick, Schulz, Julian, Tong, Meg, Hubinger, Evan, Turner, Alexander Matt
Format:	Preprint
Published:	2023
Subjects:	Computation and Language Artificial Intelligence Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
by: Ackerman, Christopher, et al.
Published: (2024)

Investigating Bias Representations in Llama 2 Chat via Activation Steering
by: Lu, Dawn, et al.
Published: (2024)

Uncovering Deceptive Tendencies in Language Models: A Simulated Company AI Assistant
by: Järviniemi, Olli, et al.
Published: (2024)

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
by: Ball, Sarah, et al.
Published: (2024)

Open Character Training: Shaping the Persona of AI Assistants through Constitutional AI
by: Maiya, Sharan, et al.
Published: (2025)

Interpretable Steering of Large Language Models with Feature Guided Activation Additions
by: Soo, Samuel, et al.
Published: (2025)

HyperSteer: Activation Steering at Scale with Hypernetworks
by: Sun, Jiuding, et al.
Published: (2025)

Steer Like the LLM: Activation Steering that Mimics Prompting
by: Heyman, Geert, et al.
Published: (2026)

Understanding In-context Learning of Addition via Activation Subspaces
by: Hu, Xinyan, et al.
Published: (2025)

Refusal in Language Models Is Mediated by a Single Direction
by: Arditi, Andy, et al.
Published: (2024)

A Practice of Post-Training on Llama-3 70B with Optimal Selection of Additional Language Mixture Ratio
by: Xi, Ningyuan, et al.
Published: (2024)

Programming Refusal with Conditional Activation Steering
by: Lee, Bruce W., et al.
Published: (2024)

SAKE: Steering Activations for Knowledge Editing
by: Scialanga, Marco, et al.
Published: (2025)

Mitigating Many-Shot Jailbreaking
by: Ackerman, Christopher M., et al.
Published: (2025)

Endogenous Resistance to Activation Steering in Language Models
by: McKenzie, Alex, et al.
Published: (2026)

Open Llama2 Model for the Lithuanian Language
by: Nakvosas, Artūras, et al.
Published: (2024)

Lugha-Llama: Adapting Large Language Models for African Languages
by: Buzaaba, Happy, et al.
Published: (2025)

Extracting Unlearned Information from LLMs with Activation Steering
by: Seyitoğlu, Atakan, et al.
Published: (2024)

Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
by: Wannan, et al.
Published: (2025)

Shifting Perspectives: Steering Vectors for Robust Bias Mitigation in LLMs
by: Siddique, Zara, et al.
Published: (2025)

Improving Instruction-Following in Language Models through Activation Steering
by: Stolfo, Alessandro, et al.
Published: (2024)

Llama-Nemotron: Efficient Reasoning Models
by: Bercovich, Akhiad, et al.
Published: (2025)

Multi-property Steering of Large Language Models with Dynamic Activation Composition
by: Scalena, Daniel, et al.
Published: (2024)

Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
by: Bigelow, Eric, et al.
Published: (2025)

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
by: Anand, Nikhil, et al.
Published: (2026)

BanglaLlama: LLaMA for Bangla Language
by: Zehady, Abdullah Khan, et al.
Published: (2024)

Contrast-CAT: Contrasting Activations for Enhanced Interpretability in Transformer-based Text Classifiers
by: Han, Sungmin, et al.
Published: (2025)

HelpSteer2-Preference: Complementing Ratings with Preferences
by: Wang, Zhilin, et al.
Published: (2024)

Extending Activation Steering to Broad Skills and Multiple Behaviours
by: van der Weij, Teun, et al.
Published: (2024)

Fragile Knowledge, Robust Instruction-Following: The Width Pruning Dichotomy in Llama-3.2
by: Martra, Pere
Published: (2025)

Forbidden Facts: An Investigation of Competing Objectives in Llama-2
by: Wang, Tony T., et al.
Published: (2023)

COLD-Steer: Steering Large Language Models via In-Context One-step Learning Dynamics
by: Sharma, Kartik, et al.
Published: (2026)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
by: Han, Pengrui, et al.
Published: (2026)

LLM Evaluators Recognize and Favor Their Own Generations
by: Panickssery, Arjun, et al.
Published: (2024)

Steering Awareness: Detecting Activation Steering from Within
by: Rivera, Joshua Fonseca, et al.
Published: (2025)

Compositional Steering of Large Language Models with Steering Tokens
by: Radevski, Gorjan, et al.
Published: (2026)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
by: Kang, Diancheng, et al.
Published: (2026)

SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
by: Batra, Shourya, et al.
Published: (2025)

Steering Language Models With Activation Engineering
by: Turner, Alexander Matt, et al.
Published: (2023)

The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"
by: Berglund, Lukas, et al.
Published: (2023)