© 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. 101357
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    Not in Any Lists

    No Comments

    Negative Logits
    了解
    -0.07
    626
    -0.06
     компон
    -0.06
    редел
    -0.06
     Serum
    -0.06
    $$$$
    -0.06
    ้ำหน
    -0.06
    Vector
    -0.06
     Rif
    -0.06
     Gloves
    -0.06
    POSITIVE LOGITS
     duygu
    0.07
    [MAXN
    0.07
    (handler
    0.07
    ection
    0.07
    [maxn
    0.07
    óm
    0.07
     콘
    0.06
     čtyři
    0.06
     doctrine
    0.06
    лем
    0.06
    Activations Density 0.033%

    No Known Activations