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. 80873
    Prev
    Next
    INDEX
    Explanations

    RBI

    np_max-act · gemini-2.0-flash

    The neuron activates on floating‐point numerical tokens—i.e. decimal statistics values (like .4089, 3.95, etc.) in the baseball‐stat context.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    specific player performance metrics and statistics in baseball.

    oai_token-act-pair · gpt-4o-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
    ươi
    -0.06
     Court
    -0.06
     đúng
    -0.06
     Sized
    -0.06
    _Ad
    -0.06
    ango
    -0.06
    /autoload
    -0.06
     Altern
    -0.06
     HERO
    -0.06
     pyplot
    -0.05
    POSITIVE LOGITS
    conut
    0.07
     Strawberry
    0.07
     Vitamin
    0.07
    ственный
    0.06
    CSI
    0.06
     thương
    0.06
    .labelX
    0.06
    у
    0.06
    layıcı
    0.06
    /block
    0.06
    Activations Density 0.001%

    No Known Activations