© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 96603
    Prev
    Next
    INDEX
    Explanations

    SQL

    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
    Not in Any Lists

    No Comments

    Negative Logits
     khởi
    -0.07
    気に入
    -0.07
     시작
    -0.07
     máme
    -0.07
    ’h
    -0.07
    に見
    -0.07
    .getView
    -0.07
     hüc
    -0.07
     jm
    -0.07
    ighet
    -0.07
    POSITIVE LOGITS
    SQL
    0.13
    sql
    0.12
     sql
    0.12
     SQL
    0.11
    /sql
    0.10
    (sql
    0.09
    _sql
    0.09
     Sql
    0.09
    .Sql
    0.08
    Sql
    0.08
    Activations Density 0.015%

    No Known Activations