© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13614
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    The neuron detects numeric tokens that are part of parenthesized statistical counts or fractions (e.g. “15/55”) reported in scientific results.

    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
    DAT
    -0.06
    	json
    -0.06
    trace
    -0.06
    [href
    -0.06
    軟
    -0.06
    address
    -0.06
    @"
    -0.06
    ertype
    -0.06
     fmt
    -0.06
    .place
    -0.06
    POSITIVE LOGITS
    mor
    0.07
    []{"
    0.06
     зел
    0.06
     الى
    0.06
    cosity
    0.06
     deductible
    0.06
     LAB
    0.06
     пы
    0.06
    ış
    0.06
     你
    0.06
    Activations Density 0.017%

    No Known Activations