© 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. 889
    Prev
    Next
    INDEX
    Explanations

    JavaScript

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of JavaScript code or files (e.g. “JS,” “javascript,” “script,” “scripts”), i.e. references to including or loading JavaScript.

    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
    ılıyor
    -0.06
    Buy
    -0.06
    �
    -0.06
    ')";↵
    -0.06
    BoundingBox
    -0.06
    xing
    -0.06
    ckt
    -0.06
    σσότε
    -0.05
    )=>{↵
    -0.05
    els
    -0.05
    POSITIVE LOGITS
    .variant
    0.06
    เขา
    0.06
     expectedResult
    0.06
    ="./
    0.06
    ोषण
    0.06
    	opts
    0.06
    .validate
    0.06
     COMMENT
    0.06
    .obtain
    0.06
    076
    0.06
    Activations Density 0.013%

    No Known Activations