© 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. 36438
    Prev
    Next
    INDEX
    Explanations

    most/best

    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
    /XML
    -0.06
     perfor
    -0.06
     cz
    -0.06
    ventions
    -0.06
     соедин
    -0.06
    نگی
    -0.06
    ipar
    -0.06
    βά
    -0.06
    響
    -0.06
     rewritten
    -0.06
    POSITIVE LOGITS
     dpi
    0.07
     ];↵
    0.07
     Junction
    0.06
    );}↵↵
    0.06
     );↵
    0.06
    Click
    0.06
    '});↵
    0.06
     click
    0.06
     employer
    0.06
    -media
    0.06
    Activations Density 0.047%

    No Known Activations