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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 13500
    Prev
    Next
    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash

    This neuron detects legal citation volume-and-page markers in court reporter references (e.g., “F.2d 2.8515625”).

    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
    baby
    -0.07
    Detection
    -0.06
    acet
    -0.06
    _DOC
    -0.06
    _In
    -0.06
    虎
    -0.06
    He
    -0.06
    ,P
    -0.06
     cực
    -0.06
    采购
    -0.06
    POSITIVE LOGITS
     Blackhawks
    0.07
    igDecimal
    0.07
     comparisons
    0.07
     Formatting
    0.06
    =").
    0.06
     Πολι
    0.06
    :maj
    0.06
    .parent
    0.06
     queues
    0.06
    雙
    0.06
    Activations Density 0.001%

    No Known Activations