© 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. 108777
    Prev
    Next
    INDEX
    Explanations

    method

    np_max-act · gemini-2.0-flash

    This neuron activates on transitional phrases that introduce or describe a specific synthetic route or reaction step (e.g. “In this reaction,” “In this route”).

    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
    Health
    -0.07
    -pressure
    -0.07
     Ice
    -0.06
    —from
    -0.06
     liệu
    -0.06
    ,在
    -0.06
     take
    -0.06
     Default
    -0.06
    —we
    -0.06
    ues
    -0.06
    POSITIVE LOGITS
    ritt
    0.07
     Mein
    0.06
     Nicht
    0.06
    addafi
    0.06
    apon
    0.06
    .Cells
    0.05
     çerçev
    0.05
    (){
    ↵
    ↵
    0.05
    ""↵
    0.05
     اسلام
    0.05
    Activations Density 0.065%

    No Known Activations