Emergent Introspective Awareness in Large Language Models
We investigate whether large language models are aware of their own internal states. It is difficult to answer this question through conversation alone, as genuine introspection cannot be distinguished from confabulations. Here, we address this challenge by injecting representations of known concepts into a model’s activations, and measuring the influence of these manipulations on the model’s self-reported states. We find that models can, in certain scenarios, notice the presence of injected concepts and accurately identify them. Models demonstrate some ability to recall prior internal representations and distinguish them from raw text inputs. Strikingly, we find that some models can use their ability to recall prior intentions in order to distinguish their own outputs from artificial prefills. In all these experiments, Claude Opus 4 and 4.1, the most capable models we tested, generally demonstrate the greatest introspective awareness; however, trends across models are complex and sens
Published October 29th, 2025 We investigate whether large language models are aware of their own internal states. It is difficult to answer this question through conversation alone, as genuine introspection cannot be distinguished from confabulations. Here, we address this challenge by injecting representations of known concepts into a model’s activations, and measuring the influence of these manipulations on the model’s self-reported states. We find that models can, in certain scenarios, notice the presence of injected concepts and accurately identify them. Models demonstrate some ability…
saved by
related reading
- Emergent introspective awareness in large language models \ Anthropicanthropic.com
- Emergent Introspective Awareness in Large Language Modelstransformer-circuits.pub
- [2601.01828] Emergent Introspective Awareness in Large Language Modelsarxiv.org
- [2601.01828] Emergent Introspective Awareness in Large Language Modelsarxiv.org
- Small Models Can Introspect, Toovgel.me
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- Detecting the Disturbance: A Nuanced View of Introspective Abilities in LLMsarxiv.org
- [2607.14111] Introspection Fine-Tuning (IFT): Training Small LLMs to Introspectarxiv.org
- A global workspace in language models \ Anthropicanthropic.com
- [2506.05068] Does It Make Sense to Speak of Introspection in Large Language Models?arxiv.org
- [2410.13787] Looking Inward: Language Models Can Learn About Themselves by Introspectionarxiv.org
- [2410.13787] Looking Inward: Language Models Can Learn About Themselves by Introspectionarxiv.org