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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RESID-POST-AA
    11. 103056
    Prev
    Next
    INDEX
    Explanations

    have

    np_max-act · gemini-2.0-flash
    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
    CUS
    -0.06
     yılı
    -0.06
    fits
    -0.06
     TURN
    -0.06
    ้องพ
    -0.06
    ré
    -0.06
    querySelector
    -0.06
    However
    -0.06
     bytesRead
    -0.06
    notify
    -0.06
    POSITIVE LOGITS
    .guid
    0.07
    ('|
    0.07
    _MAIN
    0.07
     الجن
    0.07
    loon
    0.07
    重
    0.07
    .additional
    0.07
     autopsy
    0.07
     defenseman
    0.07
    .Help
    0.07
    Activations Density 0.014%

    No Known Activations