© 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. 41346
    Prev
    Next
    INDEX
    Explanations

    court

    np_max-act · gemini-2.0-flash

    legal terminology and court case references.

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

    The neuron fires on the uppercase title lines naming the “Supreme Court of…” (i.e. the court-header phrase at the top of legal opinions).

    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
    peer
    -0.07
     provincial
    -0.07
    sending
    -0.06
    .Chat
    -0.06
    择
    -0.06
    idency
    -0.06
    查
    -0.06
    ��
    -0.06
    repeat
    -0.06
     gin
    -0.06
    POSITIVE LOGITS
     Elsa
    0.06
     моб
    0.06
    .functions
    0.06
     unhappy
    0.06
     Pacers
    0.06
     aucun
    0.06
    -existent
    0.06
    Reflect
    0.06
    фика
    0.06
    _stub
    0.06
    Activations Density 0.002%

    No Known Activations