© 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. 15-LLAMASCOPE-RES-131K
    11. 87490
    Prev
    Next
    INDEX
    Explanations

    references to COVID-19 and related topics in various contexts

    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
    bsd
    -0.07
     Hindered
    -0.06
    itzer
    -0.06
    oret
    -0.06
    iger
    -0.05
    itudes
    -0.05
     Ling
    -0.05
    erra
    -0.05
    abin
    -0.05
    ÙħØ©
    -0.05
    POSITIVE LOGITS
    ẽ
    0.07
    еннÑĸ
    0.07
     اÙĦرÙħزÙĬØ©
    0.07
    _APPEND
    0.07
     âĢİ
    0.07
    ικα
    0.06
    bij
    0.06
    пÑĢиклад
    0.06
    Äįin
    0.06
    eyin
    0.06
    Activations Density 0.020%

    No Known Activations