Backdoors have universal representations across large language models — LessWrong

by Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash, Amirali Abdullah • …

x Backdoors have universal representations across large language models — LessWrong Deceptive Alignment Interpretability (ML & AI) AI Frontpage 18 Backdoors have universal representations across large language models by Amirali Abdullah , Narmeen , Dhruv Nathawani , nirmalendu prakash 6th Dec 2024 20 min read 0 18 by Narmeen Oozeer, Dhruv Nathawani, Nirmalendu Prakash, Amirali Abdullah This work was done by Narmeen Oozeer as a research fellow at Martian, under an AI safety grant supervised by PIs Amirali Abdullah and Dhruv Nathawani. Special thanks to Sasha Hydrie, Chaithanya Bandi and Shriyas

related reading

• Natural Language Autoencoders Produce Unsupervised Explanations of LLM Activationstransformer-circuits.pub
• [2502.17424] Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMsarxiv.org
• [2604.16812] Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org
• Auditing language models for hidden objectives — LessWronglesswrong.com
• 2408.12798arxiv.org
• [2512.11949] Neural Chameleons: Language Models Can Learn to Hide Their Thoughts from Unseen Activation Monitorsarxiv.org
• Discovering Backdoor Triggers — LessWronglesswrong.com
• Mechanistically Eliciting Latent Behaviors in Language Models — AI Alignment Forumalignmentforum.org
• [2312.06942] AI Control: Improving Safety Despite Intentional Subversionarxiv.org
• Large Language Diffusion Modelsarxiv.org
• [2511.08579] Training Language Models to Explain Their Own Computationsarxiv.org
• Introspection Adapters: Training LLMs to Report Their Learned Behaviorsarxiv.org