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. 73501
    Prev
    Next
    INDEX
    Explanations

    Sports betting/live streams

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of sports fixtures—specifically the “Team vs. Team” pattern (often with “vs” or “match” and date or numeric context).

    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
     pyl
    -0.07
     Burke
    -0.07
    uche
    -0.06
    te
    -0.06
    ntity
    -0.06
     domingo
    -0.06
    eil
    -0.06
    446
    -0.06
     estimator
    -0.06
    content
    -0.06
    POSITIVE LOGITS
    gradation
    0.08
     와
    0.06
    )_
    0.06
     giy
    0.06
    (V
    0.06
     seeing
    0.06
     چرا
    0.06
    alam
    0.06
     PostgreSQL
    0.06
     implicated
    0.06
    Activations Density 0.028%

    No Known Activations