© 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. 123908
    Prev
    Next
    INDEX
    Explanations

    commas and parentheses

    np_max-act · gemini-2.0-flash

    The neuron consistently lights up on the commas, ampersands, parentheses, and identifier tokens that occur in C/C++ function or method parameter declarations—that is, the pieces of a parameter list in a signature.

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

    code-related terms related to software licensing and copyright information.

    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
    .ali
    -0.06
    Blockchain
    -0.06
     blister
    -0.06
    /Form
    -0.06
    เช
    -0.06
    cassert
    -0.06
    fcntl
    -0.06
    .position
    -0.06
    ším
    -0.06
    ular
    -0.06
    POSITIVE LOGITS
    ,test
    0.06
    waukee
    0.06
    كن
    0.06
     �
    0.06
     underwent
    0.05
     完
    0.05
     workers
    0.05
     <%
    0.05
     Вол
    0.05
     WINDOWS
    0.05
    Activations Density 0.017%

    No Known Activations