Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126777
    Prev
    Next
    INDEX
    Explanations

    division

    np_max-act · gemini-2.0-flash

    This neuron responds to the word “divided” in division‐problem statements.

    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
    东西
    -0.07
    러스
    -0.06
    лан
    -0.06
    рем
    -0.06
    Boom
    -0.06
    影響
    -0.06
     Email
    -0.06
     момент
    -0.06
     workshops
    -0.06
    در
    -0.06
    POSITIVE LOGITS
    یک
    0.07
     deciding
    0.07
     mainWindow
    0.07
    .pb
    0.06
    >"↵
    0.06
     ruth
    0.06
    mainwindow
    0.06
     surreal
    0.06
     regulate
    0.06
    ")]↵↵
    0.06
    Activations Density 0.008%

    No Known Activations