© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 68807
    Prev
    Next
    INDEX
    Explanations

    code configuration

    np_max-act · gemini-2.0-flash

    This neuron fires on C# database‐context calls—especially Entity Framework “Add” and “SaveChanges” (or similar) methods that persist data.

    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
    bank
    -0.07
    ://${
    -0.07
     Party
    -0.07
    .:.:
    -0.06
    Budget
    -0.06
     Haupt
    -0.06
     subsidies
    -0.06
     voucher
    -0.06
    Worksheet
    -0.06
    .Subject
    -0.06
    POSITIVE LOGITS
    ILER
    0.08
     الغ
    0.06
     prá
    0.06
    DEV
    0.06
     експ
    0.06
     dump
    0.06
    Autoresizing
    0.06
    ENCH
    0.06
    .OrderByDescending
    0.06
    (QStringLiteral
    0.06
    Activations Density 0.112%

    No Known Activations