© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 130044
    Prev
    Next
    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash

    The neuron fires on CSS syntax delimiters—particularly the rule-opening braces (“{”), property-value colons (“:”), and related tokens like pseudo-selector keywords (“after”) that mark CSS rule boundaries.

    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
    ilded
    -0.07
    idos
    -0.07
     costly
    -0.06
    Info
    -0.06
     vampire
    -0.06
    verts
    -0.06
    プリ
    -0.06
     Property
    -0.06
     creator
    -0.06
    db
    -0.06
    POSITIVE LOGITS
    /write
    0.08
     المتحدة
    0.07
    "`↵↵
    0.06
    {
↵
    0.06
     testosterone
    0.06
    _shortcode
    0.06
    ・・・↵↵
    0.06
    enumerate
    0.06
     Asus
    0.06
    ارية
    0.06
    Activations Density 0.008%

    No Known Activations