© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54062
    Prev
    Next
    INDEX
    Explanations

    Sports and winning

    np_max-act · gemini-2.0-flash

    The neuron strongly activates on mentions of sports scoring details—numbers, set/frame counts, game or match scores, and win/lead statistics.

    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
     accepted
    -0.06
     Bazı
    -0.06
    �
    -0.06
     پیشنه
    -0.06
    792
    -0.05
    شنامه
    -0.05
     onclick
    -0.05
    kills
    -0.05
     говор
    -0.05
     Мор
    -0.05
    POSITIVE LOGITS
    ."/
    0.07
    rico
    0.07
     parç
    0.07
     staat
    0.07
     Drugs
    0.07
    ــــــــ
    0.07
    大き
    0.07
    يرة
    0.07
    -el
    0.06
    (lon
    0.06
    Activations Density 0.009%

    No Known Activations