© 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. 126152
    Prev
    Next
    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash

    The neuron detects numeric literal tokens, especially floating‐point numbers.

    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
    ips
    -0.07
     Henderson
    -0.07
     soils
    -0.06
     proletariat
    -0.06
    ему
    -0.06
    Ru
    -0.06
     Popular
    -0.06
    ip
    -0.06
    หว
    -0.06
     scp
    -0.06
    POSITIVE LOGITS
    也是
    0.07
    zm
    0.07
    .setImage
    0.07
     muestra
    0.07
    _one
    0.07
    =[
    0.07
     $("<
    0.07
     맛
    0.06
     ≠
    0.06
    CATEGORY
    0.06
    Activations Density 0.015%

    No Known Activations