© 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. 124791
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash

    This neuron fires on streaming JavaScript method names (especially jQuery calls) appearing after “.”—for example html, show, hide, scrollTop, css, hover, etc.

    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
    _IRQHandler
    -0.07
    érer
    -0.06
     photographers
    -0.06
     prisoners
    -0.06
    _le
    -0.06
    ario
    -0.06
     Browns
    -0.06
     hardcore
    -0.06
     PNG
    -0.06
    ployment
    -0.06
    POSITIVE LOGITS
     chorus
    0.08
    >ID
    0.07
     Fay
    0.07
     Many
    0.07
     lyric
    0.07
    alarında
    0.07
     tragedy
    0.07
    (Mat
    0.06
    Appear
    0.06
    launcher
    0.06
    Activations Density 0.031%

    No Known Activations