© 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. 11-RESID-POST-AA
    11. 47207
    Prev
    Next
    INDEX
    Explanations

    Asking questions and giving advice

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    езд
    -0.07
     freund
    -0.07
     зас
    -0.07
    “A
    -0.06
     exploitation
    -0.06
     cet
    -0.06
    sprintf
    -0.06
    кий
    -0.06
    ascular
    -0.06
    면적
    -0.06
    POSITIVE LOGITS
    routeProvider
    0.06
    ,msg
    0.06
    .EventType
    0.06
     CultureInfo
    0.06
     impressive
    0.06
     parenthesis
    0.06
    postalcode
    0.06
     median
    0.06
    SESSION
    0.06
    kf
    0.06
    Activations Density 0.060%

    No Known Activations