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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 43986
    Prev
    Next
    INDEX
    Explanations

    Document ready events

    np_max-act · gemini-2.0-flash

    finds mentions of the DOM/document "ready" (page-ready/readiness) event — references to running code when the document/DOM has loaded.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     monitored
    -0.07
     subdiv
    -0.07
     mutation
    -0.07
     encoding
    -0.07
    ٣
    -0.07
    _brightness
    -0.06
    updating
    -0.06
     chapel
    -0.06
    [v
    -0.06
    енного
    -0.06
    POSITIVE LOGITS
     العق
    0.08
    (Collectors
    0.07
    profits
    0.07
    pecting
    0.06
     HttpResponseMessage
    0.06
    olygon
    0.06
     velit
    0.06
     EventArgs
    0.06
     Eagle
    0.06
     Exists
    0.06
    Activations Density 0.012%

    No Known Activations