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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 18498
    Prev
    Next
    INDEX
    Explanations

    database queries and code

    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
    <fieldset
    -0.07
    stead
    -0.06
     хими
    -0.06
    Thu
    -0.06
     Carter
    -0.06
    Console
    -0.06
    ]){↵
    -0.06
    Demand
    -0.06
    られ
    -0.06
     찾아
    -0.06
    POSITIVE LOGITS
     fseek
    0.07
     قتل
    0.07
     unused
    0.06
     Nude
    0.06
     봉
    0.06
    ooth
    0.06
     مؤس
    0.06
     Jeep
    0.06
     also
    0.06
    dbh
    0.06
    Activations Density 0.014%

    No Known Activations