© 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. 86823
    Prev
    Next
    INDEX
    Explanations

    Cities, especially Seattle

    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
    Dismiss
    -0.07
    .hibernate
    -0.06
     Rough
    -0.06
    _general
    -0.06
    xcb
    -0.06
    .nio
    -0.06
    逆
    -0.06
    .getJSONObject
    -0.06
     Hern
    -0.06
     Bart
    -0.06
    POSITIVE LOGITS
     Seattle
    0.09
    Seattle
    0.06
    Ă
    0.06
     attr
    0.06
    enko
    0.06
    reation
    0.06
    Ä
    0.06
    ität
    0.06
    xCD
    0.06
     Ever
    0.06
    Activations Density 0.113%

    No Known Activations