© 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. 79045
    Prev
    Next
    INDEX
    Explanations

    phrases related to system performance and resource utilization

    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
    kdir
    -0.07
    iggins
    -0.07
     Glo
    -0.06
    ož
    -0.06
    etros
    -0.06
    -urlencoded
    -0.06
     regimen
    -0.06
     Mass
    -0.06
     liquid
    -0.06
     compact
    -0.06
    POSITIVE LOGITS
     CPU
    0.11
     processor
    0.10
    CPU
    0.09
    processor
    0.09
     cpu
    0.09
    Processor
    0.09
     CPUs
    0.08
     processors
    0.08
     cores
    0.08
     Processor
    0.08
    Activations Density 0.065%

    No Known Activations