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. 84464
    Prev
    Next
    INDEX
    Explanations

    commercial products and services

    np_max-act · gemini-2.0-flash

    This neuron highlights mentions of financial products, services, and related business terms.

    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
     hot
    -0.08
    족
    -0.07
    quiz
    -0.07
    不存在
    -0.07
    Successful
    -0.07
     主
    -0.06
    ील
    -0.06
    delete
    -0.06
    _tensor
    -0.06
     ancient
    -0.06
    POSITIVE LOGITS
     підготов
    0.07
    JC
    0.06
    shine
    0.06
    щ
    0.06
     oi
    0.06
    -LAST
    0.06
    (ViewGroup
    0.06
     кар
    0.06
    كه
    0.06
    .isLoading
    0.06
    Activations Density 0.108%

    No Known Activations