© 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. 44608
    Prev
    Next
    INDEX
    Explanations

    pitch

    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
    Negative Logits
     bridges
    -0.08
    /operators
    -0.07
     Vil
    -0.07
    registration
    -0.06
     etwas
    -0.06
     torn
    -0.06
     computed
    -0.06
    Registration
    -0.06
    .angle
    -0.06
    Locations
    -0.06
    POSITIVE LOGITS
     HACK
    0.07
    '];
↵
    0.07
    殺
    0.07
    杀
    0.06
    でき
    0.06
    Css
    0.06
    ITableView
    0.06
    ॉ
    0.06
     unc
    0.06
    ษ
    0.06
    Activations Density 0.005%

    No Known Activations