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. 85867
    Prev
    Next
    INDEX
    Explanations

    college

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of a player's college football career (e.g., “College,” “career,” “college football,” “played college football”).

    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
    92
    -0.07
     tří
    -0.06
    ći
    -0.06
     stad
    -0.06
    Mode
    -0.06
     अ
    -0.06
    _Not
    -0.06
    icrobial
    -0.06
    (cf
    -0.06
    of
    -0.06
    POSITIVE LOGITS
    SERVER
    0.07
     consortium
    0.06
     assistants
    0.06
    .Int
    0.06
    -gap
    0.06
     discovers
    0.06
    щий
    0.06
    _handlers
    0.06
    fillType
    0.06
    .inner
    0.06
    Activations Density 0.005%

    No Known Activations