© 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. 41240
    Prev
    Next
    INDEX
    Explanations

    references to energy systems and their management, specifically focusing on distributed energy resources and grid security

    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
     Hudson
    -0.07
     finish
    -0.07
    XS
    -0.06
    egt
    -0.06
     Piper
    -0.06
    rox
    -0.06
    ieten
    -0.06
     scre
    -0.06
     Roc
    -0.06
    umph
    -0.06
    POSITIVE LOGITS
    ÙĨاÙĨ
    0.08
     Distributed
    0.08
     distributed
    0.07
     DER
    0.07
    -flex
    0.07
    etur
    0.07
    /grid
    0.07
    -grid
    0.07
     neighbourhood
    0.07
    ieg
    0.07
    Activations Density 0.015%

    No Known Activations