© 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 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. 59172
    Prev
    Next
    INDEX
    Explanations

    terms related to global health issues and disease outbreaks

    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
     Kazakhstan
    -0.07
     covid
    -0.07
    _UNIX
    -0.07
    oud
    -0.06
     Sheep
    -0.06
     COVID
    -0.06
     Neb
    -0.05
     à¹ģà¸ģ
    -0.05
     Winds
    -0.05
    æİ¢
    -0.05
    POSITIVE LOGITS
     Zika
    0.13
     mosquito
    0.10
     mosquitoes
    0.09
     tropical
    0.08
    mos
    0.07
    olin
    0.07
    زار
    0.07
     Caribbean
    0.07
    ombie
    0.07
     Mos
    0.07
    Activations Density 0.012%

    No Known Activations