© 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. 129256
    Prev
    Next
    INDEX
    Explanations

    terms related to renewable energy and sustainable technology

    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
    ãĥ³ãĤ¯
    -0.06
    urst
    -0.06
    _ISR
    -0.06
     textu
    -0.06
     nevid
    -0.06
    antro
    -0.06
     mould
    -0.06
    agy
    -0.06
    æĬ¼
    -0.06
    _tp
    -0.06
    POSITIVE LOGITS
     Gig
    0.07
     gig
    0.07
    jvu
    0.07
    Reviewer
    0.07
    Solar
    0.07
    rien
    0.07
    ylon
    0.07
     solar
    0.06
    utas
    0.06
     Solar
    0.06
    Activations Density 0.002%

    No Known Activations