© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6822
    Prev
    Next
    INDEX
    Explanations

    World Championship

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of the term “World Championship,” especially in the context of Formula One.

    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
    screens
    -0.07
     مان
    -0.07
    طور
    -0.06
    ンフ
    -0.06
    abcdefghijklmnopqrstuvwxyz
    -0.06
     rupture
    -0.06
     yeter
    -0.06
     antagon
    -0.06
     Kolkata
    -0.06
     fourn
    -0.06
    POSITIVE LOGITS
    _SUS
    0.07
    ibur
    0.07
     克
    0.06
    .shutdown
    0.06
    isory
    0.06
     ding
    0.06
     dbname
    0.06
     O
    0.06
    .Dictionary
    0.06
    .move
    0.06
    Activations Density 0.002%

    No Known Activations