© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 89870
    Prev
    Next
    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash

    The neuron detects instances of numerical data or measurements (especially 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
     dit
    -0.06
    -pill
    -0.06
    nergie
    -0.06
     purchaser
    -0.06
    _ak
    -0.06
     openings
    -0.06
     factories
    -0.06
    rand
    -0.06
    то
    -0.06
    ENC
    -0.06
    POSITIVE LOGITS
    ổng
    0.07
     Об
    0.06
    σου
    0.06
     作
    0.06
     devour
    0.06
    _apps
    0.06
    getBlock
    0.06
     Fear
    0.06
    ilestone
    0.06
    Fear
    0.06
    Activations Density 0.065%

    No Known Activations