© 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. 30159
    Prev
    Next
    INDEX
    Explanations

    terms related to energy markets and pricing

    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
    bib
    -0.07
    munition
    -0.06
    ertino
    -0.06
    سر
    -0.06
    thin
    -0.06
     punching
    -0.06
     Seattle
    -0.06
    xba
    -0.06
    ipers
    -0.06
    aukee
    -0.06
    POSITIVE LOGITS
     energy
    0.12
    energy
    0.11
     Electricity
    0.11
     electricity
    0.11
     Energy
    0.11
    Energy
    0.10
    Electric
    0.10
    _energy
    0.10
     ENERGY
    0.09
     electric
    0.09
    Activations Density 0.017%

    No Known Activations