© 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. 12236
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    This neuron detects HTML/XML markup tags (i.e. tokens beginning with “<” such as `<html>`, `<head>`, `<script>`, etc.).

    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
    /owl
    -0.06
     Suzuki
    -0.06
    лоп
    -0.06
    .Scale
    -0.06
    /tos
    -0.06
     muži
    -0.06
    (Point
    -0.06
    (TIM
    -0.06
     ترك
    -0.06
    Filename
    -0.06
    POSITIVE LOGITS
    getActiveSheet
    0.08
    _disabled
    0.07
    rians
    0.07
    ARRANT
    0.07
    (step
    0.07
     началь
    0.07
    -contact
    0.06
     demanded
    0.06
     insist
    0.06
    opened
    0.06
    Activations Density 0.028%

    No Known Activations