© 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. 108854
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron detects short, lowercase Hungarian‐notation prefixes (like “b”, “u”, “by”, “p”, etc.) on variable names in C/C++ code.

    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
     tatto
    -0.07
    .getData
    -0.07
    PX
    -0.07
    ภาคม
    -0.06
     acquaintance
    -0.06
     ateş
    -0.06
    +":
    -0.06
     symmetry
    -0.06
    compression
    -0.06
     duplicate
    -0.06
    POSITIVE LOGITS
    taxonomy
    0.07
     Jobs
    0.06
     Navy
    0.06
    _stylesheet
    0.06
    INES
    0.06
     право
    0.06
    -Benz
    0.06
     Agile
    0.06
     Rentals
    0.06
     Esc
    0.06
    Activations Density 0.012%

    No Known Activations