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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 37901
    Prev
    Next
    INDEX
    Explanations

    assistant

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of an “assistant” (especially in the context of a personal or virtual assistant).

    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
    ัฒนา
    -0.07
    _MONITOR
    -0.06
    etroit
    -0.06
    +"/
    -0.06
     clique
    -0.06
     تط
    -0.06
     유지
    -0.06
    .del
    -0.06
     Christ
    -0.06
     поли
    -0.06
    POSITIVE LOGITS
     =
    ↵
    0.06
     Yii
    0.06
    $a
    0.06
     UObject
    0.06
     Resume
    0.06
    ={
    0.06
     شخصية
    0.06
     tud
    0.06
    ":{"
    0.06
    Submitted
    0.06
    Activations Density 0.010%

    No Known Activations