© 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. 7204
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    legal terminology and case references related to criminal proceedings.

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

    The neuron detects legal case citations—references to court opinions (volume, reporter, year, docket numbers, and party names).

    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
     soil
    -0.06
    ipar
    -0.06
    _LINE
    -0.06
     minion
    -0.06
    train
    -0.06
     EST
    -0.06
     suis
    -0.06
     sensors
    -0.06
     tasted
    -0.06
    .Lines
    -0.06
    POSITIVE LOGITS
    \Customer
    0.07
     쉬
    0.07
    yet
    0.06
     acl
    0.06
    <GameObject
    0.06
    Ком
    0.06
    ()){
    0.06
    ited
    0.06
    <![
    0.06
     đồng
    0.06
    Activations Density 0.024%

    No Known Activations