© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 126273
    Prev
    Next
    INDEX
    Explanations

    INSERT

    np_max-act · gemini-2.0-flash

    This neuron detects SQL data-manipulation keywords (e.g. INSERT, UPDATE) in queries.

    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
    인증
    -0.07
    烦
    -0.07
     rivers
    -0.06
    /png
    -0.06
    说
    -0.06
     quit
    -0.06
     спортив
    -0.06
    射
    -0.06
    ภาค
    -0.06
    說
    -0.06
    POSITIVE LOGITS
    enerated
    0.06
    	namespace
    0.06
     positively
    0.06
    getX
    0.06
     chocolates
    0.06
     renderItem
    0.06
     invite
    0.06
    classCallCheck
    0.06
     acting
    0.06
     Each
    0.06
    Activations Density 0.003%

    No Known Activations