© 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. 39186
    Prev
    Next
    INDEX
    Explanations

    install

    np_max-act · gemini-2.0-flash

    The neuron fires on words involved in installation instructions for missing Python packages (e.g., “install,” “installing,” “using,” “environment,” and package names).

    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
    .slides
    -0.06
    	channel
    -0.06
     FileNotFoundException
    -0.06
     feathers
    -0.06
    _ATTACH
    -0.06
    وند
    -0.06
     /*↵
    -0.05
     Meredith
    -0.05
    Eng
    -0.05
    Meeting
    -0.05
    POSITIVE LOGITS
    Qty
    0.07
     fron
    0.06
     Amerika
    0.06
    Reports
    0.06
    .workspace
    0.06
    icators
    0.06
    ̧
    0.06
     İ
    0.06
     deserving
    0.06
    량
    0.06
    Activations Density 0.015%

    No Known Activations