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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 95535
    Prev
    Next
    INDEX
    Explanations

    terms related to data routing and replication in distributed systems

    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
     ëĦ¤ìĿ´íĬ¸
    -0.10
    rava
    -0.08
    luv
    -0.08
    ietet
    -0.08
    oman
    -0.07
    urette
    -0.07
    omain
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    umbn
    -0.07
    oard
    -0.07
    POSITIVE LOGITS
     balancing
    0.07
     available
    0.07
    borg
    0.07
     load
    0.07
     server
    0.06
     Farms
    0.06
     machines
    0.06
    load
    0.06
     Guar
    0.06
     exclusive
    0.06
    Activations Density 0.012%

    No Known Activations