© 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. 89460
    Prev
    Next
    INDEX
    Explanations

    code or programming

    np_max-act · gemini-2.0-flash

    This neuron activates on user requests for code (e.g., “provide me the code,” “give me the code,” “can you send the code,” etc.).

    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
    progressbar
    -0.07
     trọng
    -0.06
     nodes
    -0.06
    .Publish
    -0.06
    thread
    -0.06
     booths
    -0.06
     leth
    -0.06
     sell
    -0.06
    	ex
    -0.06
     propName
    -0.06
    POSITIVE LOGITS
    .Mapping
    0.06
     Marketable
    0.06
     substitutes
    0.06
    학년도
    0.06
    /ayushman
    0.06
     whistleblower
    0.06
     فکر
    0.06
    >Main
    0.06
    _backward
    0.06
    \xa
    0.06
    Activations Density 0.083%

    No Known Activations