© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14389
    Prev
    Next
    INDEX
    Explanations

    terms related to energy efficiency and consumption

    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
    ì²´
    -0.06
    vy
    -0.06
    .Extension
    -0.06
    ade
    -0.06
    uses
    -0.06
    ä½ĵ
    -0.06
    ias
    -0.06
     Woodward
    -0.06
    eda
    -0.06
    ents
    -0.05
    POSITIVE LOGITS
     consumption
    0.10
     Consumption
    0.08
     Saving
    0.07
    ãģ«ãģ¨
    0.07
    Consum
    0.07
    -saving
    0.07
    Saving
    0.07
    lichen
    0.07
    rams
    0.07
     saving
    0.07
    Activations Density 0.018%

    No Known Activations