Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 78492
    Prev
    Next
    INDEX
    Explanations

    Programming/user interface interaction

    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
     polic
    -0.07
     vitality
    -0.06
    .getAs
    -0.06
     webpage
    -0.06
    іє
    -0.06
    isEnabled
    -0.06
     minValue
    -0.06
    (),↵↵
    -0.06
     Miz
    -0.06
    _power
    -0.06
    POSITIVE LOGITS
    _SECRET
    0.07
     struct
    0.07
    Congress
    0.07
     Tradable
    0.06
     Struct
    0.06
    λλη
    0.06
    eming
    0.06
    uated
    0.06
     taped
    0.06
    'utilisation
    0.06
    Activations Density 0.003%

    No Known Activations