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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84618
    Prev
    Next
    INDEX
    Explanations

    Cup

    np_max-act · gemini-2.0-flash

    The neuron fires strongly on mentions of “Cup” competition names (e.g. “Fed Cup,” “Davis Cup”) in tennis contexts.

    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
    ){
    ↵
    ↵
    -0.06
    formats
    -0.06
     REGISTER
    -0.06
     bazı
    -0.06
    _DS
    -0.06
     Кон
    -0.06
     nep
    -0.06
    таки
    -0.06
     sha
    -0.06
     Emit
    -0.06
    POSITIVE LOGITS
     Fantastic
    0.07
    ContentView
    0.07
    blems
    0.07
    getLast
    0.06
     climb
    0.06
     overriding
    0.06
    Friendly
    0.06
     raced
    0.06
     Quentin
    0.06
    Fantastic
    0.06
    Activations Density 0.003%

    No Known Activations