© 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. 90970
    Prev
    Next
    INDEX
    Explanations

    .html

    np_max-act · gemini-2.0-flash

    The neuron fires on tokens that are part of “.html” filenames in navigation links—that is, it detects HTML page‐link tokens (the “.html” file references).

    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
     能
    -0.06
    ropriate
    -0.06
     spraying
    -0.06
     자기
    -0.06
    orpion
    -0.06
    CHANGE
    -0.06
    〉
    -0.06
     mines
    -0.06
     dört
    -0.06
    Weights
    -0.06
    POSITIVE LOGITS
    lač
    0.07
    шт
    0.07
    등록
    0.06
    .tel
    0.06
    PressEvent
    0.06
     θα
    0.06
    ults
    0.06
    ío
    0.06
     выс
    0.06
    [val
    0.06
    Activations Density 0.002%

    No Known Activations