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. 101023
    Prev
    Next
    INDEX
    Explanations

    /

    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
     тоб
    -0.08
     не
    -0.08
     Код
    -0.07
    ап
    -0.07
    'M
    -0.07
    ΑΡ
    -0.06
    ải
    -0.06
    Hey
    -0.06
     moduleName
    -0.06
    ону
    -0.06
    POSITIVE LOGITS
     nombreux
    0.06
     Width
    0.06
     :↵↵↵↵
    0.06
    plt
    0.06
    ColorBrush
    0.05
    .reset
    0.05
    ;/*
    0.05
     urb
    0.05
     LINEAR
    0.05
     соответств
    0.05
    Activations Density 0.006%

    No Known Activations