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. 7-RESID-POST-AA
    6. 129686
    Prev
    Next
    INDEX
    Explanations

    ERP components

    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
     puis
    -0.07
    ++↵
    -0.07
     схем
    -0.07
    ?>">↵
    -0.07
    .invokeLater
    -0.06
    け
    -0.06
     StringBuilder
    -0.06
    userdata
    -0.06
    Blockly
    -0.06
    oomla
    -0.06
    POSITIVE LOGITS
    证明
    0.06
    beb
    0.06
    ійс
    0.06
    _CLK
    0.06
    inned
    0.06
    тии
    0.06
     relates
    0.06
    /th
    0.06
    ustomed
    0.06
    unkt
    0.06
    Activations Density 0.067%

    No Known Activations