© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 25300
    Prev
    Next
    INDEX
    Explanations

    GC

    np_max-act · gemini-2.0-flash

    This neuron detects HTML/XML attribute names (e.g., HREF, BGCOLOR) in markup tags.

    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
    Band
    -0.06
     tímto
    -0.06
     swe
    -0.06
     comed
    -0.06
     laughing
    -0.06
     schl
    -0.06
    Marc
    -0.06
    cych
    -0.06
     týd
    -0.06
    896
    -0.06
    POSITIVE LOGITS
     громад
    0.07
    igator
    0.06
     Sustainability
    0.06
     الأ
    0.06
    иц
    0.06
    .VisualStudio
    0.06
    bat
    0.06
    麦
    0.06
    (jQuery
    0.06
    '){
    ↵
    0.06
    Activations Density 0.000%

    No Known Activations