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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57658
    Prev
    Next
    INDEX
    Explanations

    Mouse events and dragging

    np_max-act · gemini-2.0-flash

    Python code related to custom GTK handle implementations and mouse events.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron activates on terms and code patterns related to user-draggable, resizable selection rectangles or UI components (e.g., “draggable,” “resizable,” “selection,” “rectangle,” “user,” “select,” “drag”).

    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
    (request
    -0.07
    .internal
    -0.07
    。。↵↵
    -0.07
     affine
    -0.06
     THPT
    -0.06
    _loading
    -0.06
    iel
    -0.06
    itles
    -0.06
     Resets
    -0.06
     {}↵
    -0.06
    POSITIVE LOGITS
    .getD
    0.06
     verification
    0.06
    UBLE
    0.06
     concent
    0.06
    ScrollPane
    0.06
    _rev
    0.06
    าร
    0.06
    hiba
    0.06
    kem
    0.06
     trim
    0.05
    Activations Density 0.018%

    No Known Activations