© 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. 126940
    Prev
    Next
    INDEX
    Explanations

    .C

    np_max-act · gemini-2.0-flash

    This neuron detects legal case citations, specifically the “U.S. App. D.C.” (and similar) reporter abbreviations.

    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
    一度
    -0.06
    ды
    -0.06
     Thai
    -0.06
    开始
    -0.06
    .Part
    -0.06
    iples
    -0.06
     Hockey
    -0.06
    (cuda
    -0.06
    ero
    -0.06
    ]-
    -0.06
    POSITIVE LOGITS
    -gallery
    0.06
    :"<<
    0.06
    numer
    0.06
    ,url
    0.06
    Extension
    0.06
    109
    0.06
    RUN
    0.06
     NPC
    0.06
     autistic
    0.06
    $string
    0.06
    Activations Density 0.000%

    No Known Activations