© 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. 6750
    Prev
    Next
    INDEX
    Explanations

    button

    np_max-act · gemini-2.0-flash

    This neuron activates on HTML “button” elements (i.e., the `<button>` tag).

    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
    	  ↵
    -0.06
     Montgomery
    -0.06
     Italians
    -0.06
    ological
    -0.06
     Nack
    -0.06
    /se
    -0.06
    :%
    -0.06
     Spray
    -0.06
     seize
    -0.05
    typ
    -0.05
    POSITIVE LOGITS
    -button
    0.07
    [Byte
    0.07
    ्टम
    0.07
     Tomáš
    0.07
     어떤
    0.07
    .attachment
    0.06
     rift
    0.06
     minim
    0.06
     Å
    0.06
    <button
    0.06
    Activations Density 0.002%

    No Known Activations