Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 84526
    Prev
    Next
    INDEX
    Explanations

    material

    np_max-act · gemini-2.0-flash

    This neuron detects the legal term “material” (as in “material fact”) that recurs in summary-judgment standards.

    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
    \[
    -0.07
     коллек
    -0.07
     NST
    -0.07
    CreateInfo
    -0.07
    Genres
    -0.06
     sector
    -0.06
    _shapes
    -0.06
     instructor
    -0.06
     highest
    -0.06
    :last
    -0.06
    POSITIVE LOGITS
    ;margin
    0.07
     MEDIA
    0.06
    ブ
    0.06
     Validators
    0.06
    buzz
    0.06
    ٫
    0.06
    érie
    0.06
    _NAMES
    0.06
    Months
    0.06
     bakım
    0.06
    Activations Density 0.000%

    No Known Activations