© 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
    7. Resid Post - 131k
    9. 27-RESID-POST-AA
    11. 60312
    Prev
    Next
    INDEX
    Explanations

    code editors

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Encode
    -0.07
    --------------↵
    -0.07
    �
    -0.06
     мм
    -0.06
    -string
    -0.06
    elihood
    -0.06
    гал
    -0.06
     ============================================================================↵
    -0.06
    _profit
    -0.06
     дает
    -0.06
    POSITIVE LOGITS
    ("-",
    0.06
    /un
    0.06
     кол
    0.06
     {-
    0.06
     juicy
    0.06
    pretty
    0.06
     TNT
    0.06
    งช
    0.06
    /flutter
    0.06
    [of
    0.06
    Activations Density 0.090%

    No Known Activations