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. 86099
    Prev
    Next
    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    This neuron primarily detects the standalone indefinite article “a.”

    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
    success
    -0.07
     procure
    -0.06
     ¥
    -0.06
    ercul
    -0.06
     PREFIX
    -0.06
     vene
    -0.06
     ráno
    -0.06
    受
    -0.06
     RTS
    -0.06
    Ans
    -0.06
    POSITIVE LOGITS
    .React
    0.07
    <U
    0.06
     경험
    0.06
    [Boolean
    0.06
    uncio
    0.06
    .FromSeconds
    0.06
    tober
    0.06
    _INFINITY
    0.06
    lesc
    0.06
    [Double
    0.06
    Activations Density 0.092%

    No Known Activations