© 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. 79752
    Prev
    Next
    INDEX
    Explanations

    numerical data

    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
    (isset
    -0.07
    <|begin_of_text|>
    -0.06
    .raise
    -0.06
     ambit
    -0.06
    ürn
    -0.06
     gravitational
    -0.06
     кін
    -0.06
    اور
    -0.06
    menu
    -0.06
    ifier
    -0.06
    POSITIVE LOGITS
     rua
    0.07
     Ж
    0.06
    务
    0.06
    _xy
    0.06
     Нов
    0.06
    Worksheet
    0.06
     \↵
    0.06
     チ
    0.06
     chí
    0.06
     \↵↵
    0.05
    Activations Density 0.107%

    No Known Activations