© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 129685
    Prev
    Next
    INDEX
    Explanations

    reason/reasoning

    np_max-act · gemini-2.0-flash

    The neuron fires on words naming cognitive or mental processes (e.g. reasoning, memory, perception, problem-solving).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (vol
    -0.07
     cocktail
    -0.07
    tsky
    -0.06
     Altern
    -0.06
     Movie
    -0.06
     продаж
    -0.06
     explore
    -0.06
     bikes
    -0.06
     eviction
    -0.06
     golf
    -0.06
    POSITIVE LOGITS
     reasoning
    0.10
     Reason
    0.09
     reason
    0.07
    )did
    0.07
    	Random
    0.07
    Reason
    0.07
    */
↵
↵
    0.07
     переб
    0.06
    reason
    0.06
    .TestCheck
    0.06
    Activations Density 0.015%

    No Known Activations