© 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. 27-RESID-POST-AA
    11. 17487
    Prev
    Next
    INDEX
    Explanations

    Fights and violence

    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
     Нов
    -0.07
     одному
    -0.07
     též
    -0.07
    charging
    -0.06
     Parenthood
    -0.06
    umbnails
    -0.06
    joined
    -0.06
    Connecting
    -0.06
    estead
    -0.06
    veh
    -0.06
    POSITIVE LOGITS
    .[
    0.06
     disgr
    0.06
    =%.
    0.06
     apprec
    0.06
     Halo
    0.06
    ιθ
    0.06
    纪
    0.06
     σει
    0.06
    rám
    0.06
    uelle
    0.06
    Activations Density 0.073%

    No Known Activations