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

    Neuronpedia

    Jacobian LensNEW
    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. 57463
    Prev
    Next
    INDEX
    Explanations

    then

    np_max-act · gemini-2.0-flash

    This neuron detects topical category or list-item labels (e.g., “Astrology,” “Books,” “Comics,” “Dance,” “Horoscope,” etc.) in enumerated lists.

    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
     다운로드
    -0.07
    administration
    -0.06
    utivo
    -0.06
    이버
    -0.06
    bef
    -0.06
    urses
    -0.06
     kennen
    -0.06
     повинні
    -0.06
    ports
    -0.06
    .nlm
    -0.06
    POSITIVE LOGITS
     handic
    0.07
    Celebr
    0.06
     Greater
    0.06
    Helpers
    0.06
    WebSocket
    0.06
     isFirst
    0.06
    Hidden
    0.06
     způsobem
    0.06
     Confederate
    0.06
    enic
    0.06
    Activations Density 0.039%

    No Known Activations