© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126776
    Prev
    Next
    INDEX
    Explanations

    coding projects

    np_max-act · gemini-2.0-flash

    The neuron fires for numeric literals (integers or decimal numbers) in the text.

    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
     müdür
    -0.07
    .bid
    -0.07
     выбор
    -0.06
    ,test
    -0.06
     Kare
    -0.06
    cht
    -0.06
    Rub
    -0.06
     pen
    -0.06
    kle
    -0.06
     nên
    -0.06
    POSITIVE LOGITS
    原
    0.07
    _Flag
    0.06
    retty
    0.06
    .isSuccess
    0.06
     disclosure
    0.06
     detain
    0.06
    lical
    0.06
    าธ
    0.06
    ellas
    0.06
    jav
    0.06
    Activations Density 0.082%

    No Known Activations