© 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. 74612
    Prev
    Next
    INDEX
    Explanations

    comparisons of renewable energy sources to fossil fuels in terms of cost and efficiency

    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
    bach
    -0.07
    @student
    -0.07
    iterr
    -0.07
    å¼¥
    -0.07
    عب
    -0.06
    leh
    -0.06
    isle
    -0.06
     circ
    -0.06
    wm
    -0.06
     disproportion
    -0.06
    POSITIVE LOGITS
     costs
    0.08
     Costs
    0.08
     price
    0.07
     prices
    0.07
     cost
    0.07
    iver
    0.07
    olesale
    0.07
    iva
    0.06
    cost
    0.06
     cheapest
    0.06
    Activations Density 0.010%

    No Known Activations