© 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. 128862
    Prev
    Next
    INDEX
    Explanations

    UI layout

    np_max-act · gemini-2.0-flash

    The neuron fires on mentions of GUI widget and layout class names (e.g. Composite, GridLayout, GridData, Frame, JPanel), i.e. references to UI components and layout constructs in code.

    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
    auction
    -0.07
     Arn
    -0.07
    crate
    -0.07
    -abs
    -0.07
     Antwort
    -0.07
     تنظ
    -0.07
     conflict
    -0.07
    načení
    -0.06
     koruy
    -0.06
    ได
    -0.06
    POSITIVE LOGITS
     independently
    0.06
    ButtonModule
    0.06
    (car
    0.06
     harmful
    0.06
    lou
    0.06
     positivity
    0.06
    PropertyName
    0.06
     пода
    0.05
     %+
    0.05
     člověk
    0.05
    Activations Density 0.022%

    No Known Activations