© 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. 7-RESID-POST-AA
    11. 79498
    Prev
    Next
    INDEX
    Explanations

    Non-English texts

    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
     αυτά
    -0.08
    .avatar
    -0.07
     artery
    -0.07
     Bali
    -0.07
     tendency
    -0.07
    -six
    -0.07
     Rooney
    -0.07
    Gamma
    -0.07
     Owen
    -0.06
     freak
    -0.06
    POSITIVE LOGITS
    gers
    0.06
    stice
    0.06
    .orig
    0.06
    istrict
    0.06
    ページ
    0.06
    ');?></
    0.06
    %D
    0.06
    로그램
    0.06
    ,password
    0.06
    .↵
    0.06
    Activations Density 0.034%

    No Known Activations