© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 104939
    Prev
    Next
    INDEX
    Explanations

    React components, props

    np_max-act · gemini-2.0-flash

    The neuron reliably lights up on occurrences of the JavaScript “spread”/“rest” operator (the `...` syntax), especially where you see things like `...props` or `...rest` in JSX code.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    code structures and patterns related to React components.

    oai_token-act-pair · gpt-4o-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
    三级
    -0.06
    	Error
    -0.06
     Clothes
    -0.06
    ']").
    -0.06
    	Name
    -0.06
    	top
    -0.06
    userService
    -0.06
    	dt
    -0.06
     Vương
    -0.06
    ampaign
    -0.06
    POSITIVE LOGITS
    ูน
    0.07
     truncate
    0.06
     ticket
    0.06
    -Q
    0.06
     closing
    0.06
    PRO
    0.06
    06
    0.06
    ござ
    0.06
    �
    0.06
    LOB
    0.06
    Activations Density 0.008%

    No Known Activations