© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61279
    Prev
    Next
    INDEX
    Explanations

    information related to the COVID-19 variant and its effects

    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
    zek
    -0.07
    ÑĢабаÑĤ
    -0.07
     Trib
    -0.07
    cela
    -0.06
     Corpor
    -0.06
     Trigger
    -0.06
     TempData
    -0.06
     Mush
    -0.06
    [--
    -0.06
    æ°¸ä¹ħ
    -0.06
    POSITIVE LOGITS
     partition
    0.07
    partition
    0.06
     partitions
    0.06
     Recon
    0.06
    amat
    0.06
    fit
    0.06
     Partition
    0.06
     Cheney
    0.06
    ç½
    0.06
     Shane
    0.06
    Activations Density 0.008%

    No Known Activations