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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    6. 118402
    Prev
    Next
    INDEX
    Explanations

    brows

    np_max-act · gemini-2.0-flash

    indexed placeholders and other standalone numeric tokens in text (e.g., labels with underscores and digits, list counts, and numerals).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    bright
    -0.07
     ー
    -0.06
    .layer
    -0.06
    按钮
    -0.06
    .counter
    -0.06
    Vertex
    -0.06
    Todos
    -0.06
    ROI
    -0.06
    .maven
    -0.06
    řev
    -0.06
    POSITIVE LOGITS
     instit
    0.06
     Digit
    0.06
     solidarity
    0.06
     ")↵
    0.06
     Zot
    0.06
    λικά
    0.06
     staunch
    0.06
     Les
    0.06
    (@"%@",
    0.06
     ')↵
    0.06
    Activations Density 0.872%

    No Known Activations