© 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. 41526
    Prev
    Next
    INDEX
    Explanations

    given

    np_max-act · gemini-2.0-flash

    This neuron detects the word “given” (especially in “given a …”) marking the setup of a mathematical problem.

    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
    |null
    -0.06
    iei
    -0.06
     Dan
    -0.06
    Grid
    -0.06
    ssql
    -0.06
    Bean
    -0.06
     Jerseys
    -0.06
    userService
    -0.06
     berhasil
    -0.06
    .getColumn
    -0.06
    POSITIVE LOGITS
     раб
    0.07
     проблемы
    0.07
     Но
    0.06
     моя
    0.06
    设施
    0.06
     acompañ
    0.06
     симптом
    0.06
    ulmuş
    0.06
     револю
    0.06
    _TRANSFER
    0.06
    Activations Density 0.018%

    No Known Activations