© 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. 108958
    Prev
    Next
    INDEX
    Explanations

    uncertainty and possibility

    np_max-act · gemini-2.0-flash

    This neuron fires on words that convey qualification, constraint, or possibility—terms like make, more, difficult, ensure, allow, rather, opportunity, and similar hedging or conditional markers.

    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
    ッシュ
    -0.07
    _the
    -0.07
    πως
    -0.07
    ivé
    -0.06
     tímto
    -0.06
    _ONE
    -0.06
    ्ड
    -0.06
    είται
    -0.06
     violations
    -0.06
    _elt
    -0.06
    POSITIVE LOGITS
    ilan
    0.06
    ¶
    0.06
    ,lat
    0.06
    paren
    0.06
     wig
    0.06
     созд
    0.06
    (sort
    0.06
    ования
    0.06
    (background
    0.06
     فعال
    0.06
    Activations Density 0.058%

    No Known Activations