© 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. 27-RESID-POST-AA
    11. 94131
    Prev
    Next
    INDEX
    Explanations

    unprecedented

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    _tf
    -0.07
    竟
    -0.07
    (([
    -0.06
    icans
    -0.06
    <h
    -0.06
     english
    -0.06
    ⠀
    -0.06
     Heroes
    -0.06
     Clint
    -0.06
    <|begin_of_text|>
    -0.06
    POSITIVE LOGITS
     Hence
    0.07
     psyched
    0.07
     ARR
    0.07
    );


↵
    0.07
    REF
    0.07
     відповід
    0.06
     memoria
    0.06
    UEST
    0.06
    обыти
    0.06
    جه
    0.06
    Activations Density 0.742%

    No Known Activations