© 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. 7-RESID-POST-AA
    11. 93798
    Prev
    Next
    INDEX
    Explanations

    composite

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    werk
    -0.07
    šk
    -0.07
     buffalo
    -0.07
     Boo
    -0.07
    udad
    -0.07
    $/,↵
    -0.06
     Debian
    -0.06
     allegedly
    -0.06
    Campaign
    -0.06
     incididunt
    -0.06
    POSITIVE LOGITS
     CommandLine
    0.06
    [".
    0.06
    (regex
    0.06
     homosexuals
    0.06
    058
    0.06
     Foam
    0.06
     That
    0.06
     kid
    0.06
    -MM
    0.06
    0.06
    Activations Density 0.003%

    No Known Activations