© 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. 108887
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron is detecting code patterns for fetching rows from a database query (e.g. loops with mysql_fetch_assoc, executeQuery/executeReader, etc.).

    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
     sociology
    -0.07
    .Board
    -0.06
    ibration
    -0.06
    expr
    -0.06
    _HISTORY
    -0.06
    :";
    ↵
    -0.06
    -stock
    -0.06
    िर
    -0.06
    )./
    -0.06
    alk
    -0.06
    POSITIVE LOGITS
     môn
    0.07
     Gül
    0.07
    �
    0.07
     lol
    0.07
    ’elle
    0.06
     knockout
    0.06
     vinden
    0.06
     etwas
    0.06
    자를
    0.06
     memoir
    0.06
    Activations Density 0.019%

    No Known Activations