© 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. 42720
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on mentions of Python array operations—particularly when “append,” “array,” and “python” appear together.

    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
    uncate
    -0.07
     ві
    -0.07
     uğ
    -0.06
    ación
    -0.06
     Karn
    -0.06
     위치
    -0.06
    .datetime
    -0.06
     swe
    -0.06
     Mathematics
    -0.06
    Width
    -0.06
    POSITIVE LOGITS
    [root
    0.09
    FILENAME
    0.07
    ividad
    0.07
    Webpack
    0.07
     patriot
    0.06
     Catalan
    0.06
    erved
    0.06
     παρ
    0.06
    生
    0.06
     terra
    0.06
    Activations Density 0.021%

    No Known Activations