© 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. 87657
    Prev
    Next
    INDEX
    Explanations

    numbers in patents/phone numbers

    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
     Civ
    -0.07
     continua
    -0.07
     organs
    -0.07
     XII
    -0.06
    cích
    -0.06
     dni
    -0.06
     grids
    -0.06
     hsv
    -0.06
     Eve
    -0.06
     sectors
    -0.06
    POSITIVE LOGITS
     Walton
    0.08
     첨부파일
    0.07
    忠
    0.07
    ullivan
    0.07
     <!--[
    0.07
    /help
    0.07
    skip
    0.07
    _PROVIDER
    0.07
     помощ
    0.07
     ราย
    0.07
    Activations Density 0.059%

    No Known Activations