© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109867
    Prev
    Next
    INDEX
    Explanations

    XML Schemas

    np_max-act · gemini-2.0-flash

    This neuron specializes in detecting XML/HTML–style markup, particularly lines containing tags, attributes, and schema declarations.

    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
     poured
    -0.07
    .getColumnIndex
    -0.07
    bbing
    -0.07
     Abby
    -0.07
     desperation
    -0.06
     habitats
    -0.06
    identify
    -0.06
     Eleven
    -0.06
    olders
    -0.06
    reements
    -0.06
    POSITIVE LOGITS
     minority
    0.07
    НЯ
    0.06
     armor
    0.06
    _proj
    0.06
     grop
    0.06
     mø
    0.06
     metavar
    0.06
     бороть
    0.06
    (Editor
    0.06
     toughness
    0.06
    Activations Density 0.002%

    No Known Activations