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

    Neuronpedia

    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. 127663
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific classification in biology

    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
    оÑģлав
    -0.08
    inspace
    -0.08
    ÑģÑĤеÑĢ
    -0.07
    ernetes
    -0.07
    osen
    -0.07
    serter
    -0.07
     meiden
    -0.07
    ãĤ¹ãĥĨãĥł
    -0.07
    ıy
    -0.07
    ÑĩеÑĤ
    -0.07
    POSITIVE LOGITS
    atic
    0.07
    meric
    0.06
     bur
    0.06
    art
    0.06
    re
    0.06
    679
    0.06
    omy
    0.06
     Supply
    0.06
     Bros
    0.06
    istan
    0.06
    Activations Density 0.001%

    No Known Activations