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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41031
    Prev
    Next
    INDEX
    Explanations

    base

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “source,” “code,” “application,” “project,” and similar software/code–related terms.

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

    Mentions of source code and programming tasks—especially extracting or inspecting code and API endpoints from a project.

    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_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
    aker
    -0.07
    วล
    -0.07
    엄
    -0.06
     dysfunction
    -0.06
    );}↵↵
    -0.06
    Fuse
    -0.06
     ber
    -0.06
     demonstration
    -0.06
    ните
    -0.06
    _V
    -0.06
    POSITIVE LOGITS
     toán
    0.07
     Spicer
    0.06
     Marvin
    0.06
    .ReadLine
    0.06
    _PTR
    0.06
    -haired
    0.06
    .Win
    0.06
    @g
    0.06
    -media
    0.06
    atisf
    0.06
    Activations Density 0.506%

    No Known Activations