© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 77138
    Prev
    Next
    INDEX
    Explanations

    marine

    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
    ('@
    -0.07
    iydi
    -0.07
    .Aggressive
    -0.07
    ınızı
    -0.07
    iza
    -0.06
    .maven
    -0.06
     shaft
    -0.06
    .heap
    -0.06
    іш
    -0.06
     crushers
    -0.06
    POSITIVE LOGITS
    sponsor
    0.07
     века
    0.06
     seiz
    0.06
     быть
    0.06
     orang
    0.06
     кас
    0.06
    Deaths
    0.06
    禁
    0.06
     demons
    0.06
    cheap
    0.06
    Activations Density 0.002%

    No Known Activations