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. 40579
    Prev
    Next
    INDEX
    Explanations

    sports

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of specific sports (e.g. softball, soccer, tennis).

    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
    odon
    -0.07
    results
    -0.07
    เธอ
    -0.06
     shells
    -0.06
     Seat
    -0.06
     crossing
    -0.06
    HEST
    -0.06
     schön
    -0.06
     reckless
    -0.05
     Olsen
    -0.05
    POSITIVE LOGITS
    .undefined
    0.07
    棋
    0.07
    ‰
    0.07
    SuccessListener
    0.07
    із
    0.07
    ,err
    0.07
    ">',
    0.07
    -highlight
    0.06
     místní
    0.06
    ">
    ↵
    0.06
    Activations Density 0.006%

    No Known Activations