© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 74630
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to Express.js framework routing and middleware

    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
    ouv
    -0.06
    аÑĢÑĩ
    -0.06
     distr
    -0.06
     clue
    -0.06
    AdapterFactory
    -0.06
    licted
    -0.06
    reamble
    -0.06
    alten
    -0.06
    usercontent
    -0.05
    gth
    -0.05
    POSITIVE LOGITS
     routes
    0.09
    è·¯
    0.08
    lette
    0.08
    /routes
    0.08
     route
    0.08
    Sensitive
    0.07
    -route
    0.07
    route
    0.07
     Routes
    0.07
    pattern
    0.07
    Activations Density 0.035%

    No Known Activations