© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 18779
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     urgent
    -0.07
     frankly
    -0.06
     slider
    -0.06
    pron
    -0.06
     distant
    -0.06
     بندی
    -0.06
     begs
    -0.06
     GRID
    -0.06
     actually
    -0.06
     wcs
    -0.06
    POSITIVE LOGITS
    ende
    0.07
    ию
    0.07
     ソ
    0.06
    ad
    0.06
    ламент
    0.06
    _io
    0.06
    $errors
    0.06
    ư
    0.06
    .QRect
    0.06
     експ
    0.06
    Activations Density 0.005%

    No Known Activations