© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30694
    Prev
    Next
    INDEX
    Explanations

    Expressing opinions/thoughts

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—digits, numbers (including decimals), dates, and list indices—identifying any numeric expression 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
    .clf
    -0.08
    状況
    -0.07
    ضر
    -0.06
     TIME
    -0.06
    。他
    -0.06
    _SERVER
    -0.06
    sort
    -0.06
    .Exception
    -0.06
    [X
    -0.06
    _DE
    -0.06
    POSITIVE LOGITS
    ward
    0.07
    (firstName
    0.07
    ніст
    0.06
    reply
    0.06
    níkem
    0.06
     trồng
    0.06
    .FETCH
    0.06
     конечно
    0.06
     полов
    0.06
     المف
    0.06
    Activations Density 0.189%

    No Known Activations