© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 110450
    Prev
    Next
    INDEX
    Explanations

    biographies

    np_max-act · gemini-2.0-flash

    This neuron fires on list and outline markers—numbers, numbered bullets, section or item labels (e.g. “1.”, “2)”, Roman numerals) that structure a document.

    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
    Textures
    -0.07
     yılı
    -0.07
     /**↵
    -0.06
    amma
    -0.06
    TouchEvent
    -0.06
    ái
    -0.06
     advocates
    -0.06
     Lara
    -0.06
    Target
    -0.06
    Ë
    -0.06
    POSITIVE LOGITS
    /connection
    0.07
    [hash
    0.07
     및
    0.06
    _uuid
    0.06
     intercept
    0.06
     oltre
    0.06
    _cons
    0.05
    ерб
    0.05
    $product
    0.05
    hunt
    0.05
    Activations Density 0.060%

    No Known Activations