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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 40628
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric constants (digits and numbers) within mathematical expressions.

    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
     очи
    -0.07
    مت
    -0.07
     ecs
    -0.07
    StorageSync
    -0.06
     compartir
    -0.06
    .Itoa
    -0.06
     ương
    -0.06
    ерап
    -0.06
    WithTag
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Vent
    0.07
     pursuits
    0.06
    ively
    0.06
    ummy
    0.06
    ₀
    0.06
     economists
    0.06
     fifth
    0.06
     GST
    0.06
    ivet
    0.06
     waived
    0.06
    Activations Density 0.004%

    No Known Activations