© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 38299
    Prev
    Next
    INDEX
    Explanations

    legal opinions

    np_max-act · gemini-2.0-flash

    The neuron activates on the formal case‐caption and docket‐header formatting of court opinions—i.e. the “United States Court of Appeals for … No. XX-XXX” style legal header.

    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
     bottom
    -0.07
     学
    -0.06
     worms
    -0.06
     exhibits
    -0.06
     measuring
    -0.06
     Acres
    -0.06
     Trojan
    -0.06
    periments
    -0.06
     outputStream
    -0.06
     Tem
    -0.06
    POSITIVE LOGITS
    üslü
    0.06
     sklearn
    0.06
    خف
    0.06
     Isabel
    0.06
    .avi
    0.06
    LIC
    0.06
    acimiento
    0.06
    velt
    0.06
    ZeroWidthSpace
    0.06
     Helpful
    0.06
    Activations Density 0.009%

    No Known Activations