© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55865
    Prev
    Next
    INDEX
    Explanations

    university sports teams

    np_max-act · gemini-2.0-flash

    This neuron detects the names of colleges or universities (the geographic/institutional identifiers) in sports team titles.

    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
    ipeline
    -0.07
    isto
    -0.07
    алося
    -0.06
     kr
    -0.06
    OAuth
    -0.06
    _PERIOD
    -0.06
     Slot
    -0.06
    /hooks
    -0.06
    adium
    -0.06
     While
    -0.06
    POSITIVE LOGITS
     기능
    0.06
    _V
    0.06
     dinners
    0.06
    PARAM
    0.06
     roofing
    0.06
     حي
    0.06
    .getResources
    0.06
    _PROJECT
    0.06
    迅
    0.06
    (argc
    0.06
    Activations Density 0.009%

    No Known Activations