© 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. 54120
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens—especially decimal numbers and other quantitative values—flagging statistics, measurements, and other numeric data 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
    Unless
    -0.07
    .Navigate
    -0.06
    ComputedStyle
    -0.06
    肌
    -0.06
    Dates
    -0.06
    (newValue
    -0.06
    covers
    -0.06
     Forms
    -0.06
     kHz
    -0.06
    Tumblr
    -0.06
    POSITIVE LOGITS
     bron
    0.07
     sağ
    0.07
     ağ
    0.07
    情况
    0.07
    _protocol
    0.07
    -abs
    0.06
    ormal
    0.06
     FILTER
    0.06
     strict
    0.06
     gibi
    0.06
    Activations Density 0.067%

    No Known Activations