© 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. 19-RESID-POST-AA
    11. 108516
    Prev
    Next
    INDEX
    Explanations

    university affiliation

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sequential
    -0.07
     Clim
    -0.07
    Sprite
    -0.06
    .Concurrent
    -0.06
    Dam
    -0.06
     squarely
    -0.06
     REQ
    -0.06
    참
    -0.06
    聚
    -0.06
     Herr
    -0.06
    POSITIVE LOGITS
    머
    0.07
    mons
    0.06
    mary
    0.06
    _cross
    0.06
     neighbour
    0.06
    (first
    0.06
    -heart
    0.06
    -ли
    0.06
    ro
    0.06
    no
    0.06
    Activations Density 0.031%

    No Known Activations