© 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. 74163
    Prev
    Next
    INDEX
    Explanations

    Schema

    np_max-act · gemini-2.0-flash

    This neuron detects XML schema definition attributes, in particular the “xsi:schemaLocation” (and related XML Schema namespace) declarations.

    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
     поск
    -0.07
    --------------------------------------------------------------------------------
    -0.07
    .teacher
    -0.07
     تست
    -0.07
     pisc
    -0.07
    はず
    -0.07
     mirrors
    -0.06
    adero
    -0.06
     götür
    -0.06
    ประกาศ
    -0.06
    POSITIVE LOGITS
     useContext
    0.06
    schemas
    0.06
    алення
    0.06
    iative
    0.06
    osaur
    0.06
    chantment
    0.06
     Tel
    0.06
     Blu
    0.06
    -figure
    0.06
     이
    0.06
    Activations Density 0.001%

    No Known Activations