© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43349
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron fires on the openings of code/markup blocks—e.g. CSS at‐rules like “@font‐face {” or HTML tag‐start tokens such as “<script>” or “<tr …>.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
    хід
    -0.06
     CCP
    -0.06
    _dev
    -0.06
     Should
    -0.06
     beast
    -0.06
     navigator
    -0.06
     ingredients
    -0.06
     từ
    -0.06
    Should
    -0.06
    C
    -0.06
    POSITIVE LOGITS
    vine
    0.08
    IO
    0.08
    reta
    0.07
    io
    0.07
    ственное
    0.07
    uida
    0.07
    OptionPane
    0.07
    озд
    0.07
    óng
    0.07
    ّت
    0.07
    Activations Density 0.069%

    No Known Activations