© 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. 55681
    Prev
    Next
    INDEX
    Explanations

    key components and functions related to routing in web applications

    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
     Locker
    -0.07
    RAINT
    -0.07
     abstract
    -0.06
    quip
    -0.06
     em
    -0.06
    ICAST
    -0.06
    abox
    -0.06
    hus
    -0.06
    à¹Ģà¸ķ
    -0.06
    ÑĢÑĸп
    -0.06
    POSITIVE LOGITS
    _fds
    0.07
    Sac
    0.07
    è·¯
    0.07
    Pattern
    0.07
     routes
    0.07
    Patterns
    0.07
    Ŀ
    0.07
    pattern
    0.07
    matcher
    0.07
     trục
    0.06
    Activations Density 0.001%

    No Known Activations