© 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. 90816
    Prev
    Next
    INDEX
    Explanations

    bars scrollbars

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of scrollbars or scrolling controls (e.g. “scroll,” “bars,” “overflow” settings).

    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
     Selenium
    -0.06
     زی
    -0.06
     LDS
    -0.06
    $category
    -0.06
     hangs
    -0.06
     emphasizes
    -0.06
    sus
    -0.06
     comfy
    -0.06
    อห
    -0.06
    等
    -0.06
    POSITIVE LOGITS
     человека
    0.07
    оком
    0.07
     GN
    0.07
     elev
    0.06
    UTC
    0.06
     ESC
    0.06
    inese
    0.06
     березня
    0.06
    olicies
    0.06
    193
    0.06
    Activations Density 0.003%

    No Known Activations