© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 89383
    Prev
    Next
    INDEX
    Explanations

    saliva and salivary glands

    np_max-act · gemini-2.0-flash

    references to saliva and its components in medical and physiological contexts.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of saliva or salivary secretions (e.g., “salivary,” “saliva”).

    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
     Kn
    -0.07
     Weinstein
    -0.06
    远
    -0.06
     těchto
    -0.06
     vegan
    -0.06
     coorden
    -0.06
    _BOOLEAN
    -0.06
    遠
    -0.06
     weg
    -0.06
     Hulk
    -0.06
    POSITIVE LOGITS
     saliva
    0.10
    ือ
    0.07
     appet
    0.06
     بازی
    0.06
     Romero
    0.06
     relev
    0.06
     τέ
    0.06
    ΑΜ
    0.06
    ival
    0.06
     YYSTYPE
    0.06
    Activations Density 0.002%

    No Known Activations