© 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. 15-LLAMASCOPE-RES-131K
    11. 1380
    Prev
    Next
    INDEX
    Explanations

    references to energy services and market comparisons

    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
    thin
    -0.07
    lobals
    -0.07
     Gür
    -0.07
    amage
    -0.06
    TOTYPE
    -0.06
    IRM
    -0.06
    INUX
    -0.06
    éı
    -0.06
    ipo
    -0.06
     Bos
    -0.06
    POSITIVE LOGITS
     energy
    0.11
    energy
    0.09
     Energy
    0.09
     electricity
    0.09
     Electricity
    0.08
    Energy
    0.08
     carbon
    0.07
     ENERGY
    0.07
     nuclear
    0.07
     electric
    0.07
    Activations Density 0.010%

    No Known Activations