© 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. 69855
    Prev
    Next
    INDEX
    Explanations

    terms related to online learning platforms and their courses

    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
    ario
    -0.06
     holding
    -0.06
    ÃŃr
    -0.06
     felt
    -0.06
     Canterbury
    -0.06
    ç´Ģ
    -0.05
     extended
    -0.05
     hook
    -0.05
    -quote
    -0.05
     meeting
    -0.05
    POSITIVE LOGITS
     Ud
    0.10
     course
    0.09
    thon
    0.09
     edx
    0.08
     Cour
    0.08
    à¸Ńà¸Ńà¸Ļà¹Ħลà¸Ļ
    0.07
    imed
    0.07
     HelloWorld
    0.07
     lear
    0.07
     courses
    0.07
    Activations Density 0.010%

    No Known Activations