© 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. 116061
    Prev
    Next
    INDEX
    Explanations

    df

    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
     studs
    -0.07
    .ham
    -0.07
    ambio
    -0.06
     participants
    -0.06
    енсив
    -0.06
     crossings
    -0.06
     thuis
    -0.06
    Margins
    -0.06
     Rooney
    -0.06
     explan
    -0.06
    POSITIVE LOGITS
     RDF
    0.08
    .Comm
    0.07
    __.'/
    0.07
    .Mongo
    0.06
    esel
    0.06
    ishi
    0.06
    Physical
    0.06
    .TYPE
    0.06
     rallied
    0.06
    Possible
    0.06
    Activations Density 0.003%

    No Known Activations