© 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. 11-RESID-POST-AA
    11. 101285
    Prev
    Next
    INDEX
    Explanations

    Finding regions, genes

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ワ
    -0.08
     Wil
    -0.07
     patch
    -0.07
    .OrderBy
    -0.07
    PRICE
    -0.06
     PAR
    -0.06
    BeenCalled
    -0.06
    血
    -0.06
    INDEX
    -0.06
    _EMIT
    -0.06
    POSITIVE LOGITS
    colm
    0.07
     Certain
    0.06
    Feels
    0.06
     surely
    0.06
     Enhanced
    0.06
    ์ฟ
    0.06
    Containing
    0.06
     Furn
    0.06
     Genç
    0.06
    특
    0.06
    Activations Density 0.084%

    No Known Activations