© 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. 70270
    Prev
    Next
    INDEX
    Explanations

    terms related to auroras and atmospheric phenomena

    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
    oger
    -0.07
    oyo
    -0.06
     putas
    -0.06
    beros
    -0.06
    antium
    -0.06
    oshi
    -0.06
    hurst
    -0.06
    tura
    -0.06
    edad
    -0.06
     Quarry
    -0.06
    POSITIVE LOGITS
     Northern
    0.09
     phenomenon
    0.08
     northern
    0.08
    hem
    0.08
     nights
    0.08
     phenomena
    0.08
    Northern
    0.07
     night
    0.07
     aur
    0.07
     åĮĹ
    0.07
    Activations Density 0.001%

    No Known Activations