© 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. 89712
    Prev
    Next
    INDEX
    Explanations

    block

    np_max-act · gemini-2.0-flash

    The neuron activates on code that changes an element’s visibility (e.g. setting style.display or calling show()/hide()), i.e. on statements that toggle a DOM element’s display.

    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
     backstage
    -0.06
     ghế
    -0.06
     Bootstrap
    -0.06
    aram
    -0.06
     As
    -0.06
     Congressman
    -0.06
     Aus
    -0.06
    .setSize
    -0.06
     stu
    -0.06
     dow
    -0.06
    POSITIVE LOGITS
    ');↵
    0.07
    uffers
    0.07
    ète
    0.06
     explan
    0.06
     verbally
    0.06
     Türkçe
    0.06
    _Account
    0.06
     récup
    0.06
    %A
    0.06
    -chat
    0.06
    Activations Density 0.008%

    No Known Activations