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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 39062
    Prev
    Next
    INDEX
    Explanations

    Continuing a thought

    np_max-act · gemini-2.0-flash

    This neuron activates on programming‐code contexts—especially when the user asks to continue or write code (e.g. “code,” “continue,” language names like “python”).

    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
    禁止
    -0.07
     Finding
    -0.06
    ,on
    -0.06
     miners
    -0.06
    şk
    -0.06
     Nicol
    -0.06
     Tah
    -0.06
     بنا
    -0.06
     onCancel
    -0.06
     notified
    -0.06
    POSITIVE LOGITS
     ще
    0.07
    _empresa
    0.06
     Cust
    0.06
     Mata
    0.06
    četně
    0.06
    iciente
    0.06
    ]='\
    0.06
     розвитку
    0.06
     مجموعه
    0.06
     ש
    0.06
    Activations Density 0.019%

    No Known Activations