© 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
    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. 128660
    Prev
    Next
    INDEX
    Explanations

    CREATE

    np_max-act · gemini-2.0-flash

    The neuron fires on “CREATE” (and its language variants, e.g. “CRIA”) tokens indicating the start of a definition or creation statement.

    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
    .WebServlet
    -0.08
     plunged
    -0.07
    -party
    -0.07
     consent
    -0.07
     kunt
    -0.07
     pow
    -0.06
     texte
    -0.06
     numbers
    -0.06
     kid
    -0.06
    Programming
    -0.06
    POSITIVE LOGITS
    ervice
    0.07
    ?>/
    0.07
     CGSizeMake
    0.07
    ὶ
    0.07
    FIX
    0.06
    ρκεια
    0.06
    CREATE
    0.06
    /OR
    0.06
    (!_
    0.06
    >Date
    0.06
    Activations Density 0.005%

    No Known Activations