© 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. 129841
    Prev
    Next
    INDEX
    Explanations

    drop

    np_max-act · gemini-2.0-flash

    The neuron is looking for SQL DDL commands—especially the “DROP … TABLE/SEQUENCE/PROCEDURE” statements.

    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
     raster
    -0.07
    umuz
    -0.07
    _gamma
    -0.07
    نسية
    -0.07
     recognize
    -0.06
    [tag
    -0.06
    azi
    -0.06
    _SET
    -0.06
    舌
    -0.06
     mirrors
    -0.06
    POSITIVE LOGITS
     NSRange
    0.06
     CSRF
    0.06
    utschein
    0.06
     okum
    0.06
    .Pe
    0.06
     Tradable
    0.06
     MANY
    0.06
     pepp
    0.06
     convertible
    0.06
     alot
    0.06
    Activations Density 0.003%

    No Known Activations