© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 127902
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and components, particularly in the context of React and UI frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RuntimeObject
    -0.06
    eki
    -0.06
    /controllers
    -0.06
    oyer
    -0.06
    .Java
    -0.06
    uong
    -0.06
    _php
    -0.06
    ollar
    -0.06
     AppleWebKit
    -0.06
    plist
    -0.06
    POSITIVE LOGITS
    ui
    0.08
    ¦
    0.07
     Halk
    0.07
     ui
    0.07
    UI
    0.07
    acades
    0.07
    erce
    0.07
    lix
    0.06
    ãĥ¼ãĥł
    0.06
    antine
    0.06
    Activations Density 0.016%

    No Known Activations