© 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. 15-RESID-POST-AA
    11. 27998
    Prev
    Next
    INDEX
    Explanations

    property

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ành
    -0.07
    Using
    -0.07
    равиль
    -0.07
    Match
    -0.06
    assador
    -0.06
     完
    -0.06
     Hort
    -0.06
    κ
    -0.06
    oid
    -0.06
    ライ
    -0.06
    POSITIVE LOGITS
    (station
    0.06
    .feature
    0.06
     ores
    0.06
    Cycle
    0.06
    shield
    0.06
    -nine
    0.06
    italic
    0.06
     культуры
    0.06
     INTERRU
    0.06
     clutter
    0.06
    Activations Density 0.002%

    No Known Activations