© 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. 117068
    Prev
    Next
    INDEX
    Explanations

    in

    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
    整
    -0.07
     Clip
    -0.07
    _shutdown
    -0.07
    _courses
    -0.06
     \\↵
    -0.06
    vector
    -0.06
     prep
    -0.06
     Entries
    -0.06
    _CODE
    -0.06
     booked
    -0.06
    POSITIVE LOGITS
     lorsque
    0.07
     imperson
    0.07
    krét
    0.07
     الرو
    0.07
     спок
    0.07
     squarely
    0.07
    °N
    0.06
     prima
    0.06
     ناح
    0.06
    (ac
    0.06
    Activations Density 0.028%

    No Known Activations