© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3923
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental impact and carbon measurement

    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
    teÅŁ
    -0.07
     contingency
    -0.06
    æıIJ
    -0.06
     dele
    -0.06
     protective
    -0.06
    (age
    -0.06
    èĩ¨
    -0.06
     اÙĦعظ
    -0.06
    /Foundation
    -0.06
    432
    -0.06
    POSITIVE LOGITS
     carbon
    0.08
     disag
    0.07
    anes
    0.07
     bas
    0.07
     accounting
    0.07
     GH
    0.07
    carbon
    0.07
     greenhouse
    0.07
     invent
    0.06
    etro
    0.06
    Activations Density 0.004%

    No Known Activations