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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 85648
    Prev
    Next
    INDEX
    Explanations

    sports teams and seasons

    np_max-act · gemini-2.0-flash

    The neuron spotlights mentions of sports team or club names (e.g. “Adelaide Football Club,” “D.C. United,” “Boston Bruins,” etc.).

    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
    坂
    -0.07
     Constant
    -0.07
     Ho
    -0.07
    енні
    -0.06
    croft
    -0.06
    ani
    -0.06
     experiencing
    -0.06
    زا
    -0.06
    Hu
    -0.06
     Sak
    -0.06
    POSITIVE LOGITS
     BTC
    0.07
    .getDouble
    0.07
    (InputStream
    0.07
    тив
    0.06
    _system
    0.06
    [now
    0.06
    _poll
    0.06
    ICS
    0.06
    打
    0.06
    <IM
    0.06
    Activations Density 0.018%

    No Known Activations