© 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. 19-RESID-POST-AA
    11. 123923
    Prev
    Next
    INDEX
    Explanations

    imitives

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ({"
    -0.06
     understood
    -0.06
     median
    -0.06
     published
    -0.06
     leveling
    -0.06
     suite
    -0.06
    &type
    -0.06
     अत
    -0.06
    /settings
    -0.06
    _PROJECT
    -0.06
    POSITIVE LOGITS
    (tree
    0.07
    Chr
    0.07
     Scotch
    0.07
     GameController
    0.07
     precisa
    0.06
     Sy
    0.06
    918
    0.06
     RO
    0.06
    ■■
    0.06
    owards
    0.06
    Activations Density 0.000%

    No Known Activations