© 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. 9-LLAMASCOPE-RES-131K
    11. 96359
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical equations, particularly the Navier-Stokes equations and their solutions

    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
    {return
    -0.06
    igest
    -0.06
    usercontent
    -0.06
    ãĥ¼ãĥł
    -0.06
     khá»ıi
    -0.06
    artz
    -0.06
    ulur
    -0.06
    ude
    -0.06
     PHONE
    -0.06
    anging
    -0.06
    POSITIVE LOGITS
    翼
    0.07
    office
    0.06
    ết
    0.06
    (MPI
    0.06
    _flutter
    0.06
    acy
    0.06
     Waves
    0.06
    PAIR
    0.06
    лоп
    0.06
    LEE
    0.06
    Activations Density 0.145%

    No Known Activations