© 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. 95645
    Prev
    Next
    INDEX
    Explanations

    references to the Omicron variant of COVID-19

    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
    èħIJ
    -0.08
    elin
    -0.07
    ETO
    -0.07
    ÏįÏĢ
    -0.06
    Spoiler
    -0.06
    евиÑĩ
    -0.06
    ë°Ģ
    -0.06
    emin
    -0.06
    вок
    -0.06
     Stanton
    -0.06
    POSITIVE LOGITS
     variant
    0.09
     variants
    0.07
    omic
    0.07
    variant
    0.07
    mania
    0.06
    ologna
    0.06
    dition
    0.06
    æħ§
    0.06
    inity
    0.06
     Schwarz
    0.06
    Activations Density 0.003%

    No Known Activations