© 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. 74021
    Prev
    Next
    INDEX
    Explanations

    ender

    np_max-act · gemini-2.0-flash

    This neuron activates on the XML configuration tag “appender” (i.e. parts of the word “appender”) in log4j config files.

    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
     crushing
    -0.06
    .Interop
    -0.06
    Orientation
    -0.06
     nickel
    -0.06
    ζη
    -0.06
    ذیر
    -0.06
     certifications
    -0.06
    廠
    -0.06
    Warehouse
    -0.06
    奧
    -0.06
    POSITIVE LOGITS
    (Canvas
    0.07
     Caught
    0.07
     QC
    0.06
     laying
    0.06
     پس
    0.06
     Him
    0.06
    uit
    0.06
    uy
    0.06
     sui
    0.06
     ansible
    0.06
    Activations Density 0.002%

    No Known Activations