© 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. 57652
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find programming‐style identifiers (e.g. variable, function, and model names) and other code tokens in technical text.

    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
     tn
    -0.06
    _challenge
    -0.06
    熱
    -0.06
    _variable
    -0.06
    _bill
    -0.06
     POLIT
    -0.06
     الث
    -0.06
     Value
    -0.06
    flash
    -0.06
    请输入
    -0.06
    POSITIVE LOGITS
    (pthread
    0.08
    (loss
    0.07
    usted
    0.07
     ресурс
    0.06
    -scroll
    0.06
    ’.↵↵
    0.06
     labore
    0.06
    /////
    0.06
    _svg
    0.06
    **,
    0.06
    Activations Density 0.079%

    No Known Activations