© 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. 128468
    Prev
    Next
    INDEX
    Explanations

    span

    np_max-act · gemini-2.0-flash

    The neuron is detecting HTML “span” elements (and their class attributes) used for syntax‐highlighted code snippets.

    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
    Vectors
    -0.07
    giene
    -0.06
    (ad
    -0.06
    Everything
    -0.06
     charities
    -0.06
    _inverse
    -0.06
    Ocean
    -0.06
    verter
    -0.06
    adapt
    -0.06
    	random
    -0.06
    POSITIVE LOGITS
    '>"
    0.07
    assandra
    0.07
    ={[
    0.07
     IOError
    0.07
     голова
    0.06
     Fecha
    0.06
    storybook
    0.06
    .ToDecimal
    0.06
    ']):↵
    0.06
     WHY
    0.06
    Activations Density 0.002%

    No Known Activations