© 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. 126949
    Prev
    Next
    INDEX
    Explanations

    punctuation/symbols

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of project file names (i.e. tokens containing a filename with extension, like “main.py” or “requirements.txt”).

    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
    .firstname
    -0.07
     DESCRIPTION
    -0.06
     ire
    -0.06
    촌
    -0.06
    oco
    -0.06
    оба
    -0.06
     responseObject
    -0.06
    supports
    -0.06
    .echo
    -0.06
    Rnd
    -0.06
    POSITIVE LOGITS
     adopted
    0.07
    (infile
    0.07
     Technology
    0.07
     conveniently
    0.07
    {}\
    0.06
     headed
    0.06
     upside
    0.06
     uncomfort
    0.06
    elaide
    0.06
    -category
    0.06
    Activations Density 0.181%

    No Known Activations