© 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. 129886
    Prev
    Next
    INDEX
    Explanations

    order

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “order” (e.g. property, element, or field names named order) 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
    _union
    -0.06
     waiting
    -0.06
    _word
    -0.06
    країн
    -0.06
    always
    -0.06
    ark
    -0.06
     certificate
    -0.06
    National
    -0.06
    asions
    -0.06
     surrounding
    -0.06
    POSITIVE LOGITS
     Connection
    0.06
     бли
    0.06
     провед
    0.06
     corre
    0.06
                                                                       
    0.06
    养
    0.06
    """.
    0.06
                                                   
    0.06
    {|
    0.06
     зави
    0.06
    Activations Density 0.009%

    No Known Activations