© 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. 9-LLAMASCOPE-RES-131K
    11. 97421
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols related to differential equations, specifically for the Navier-Stokes equations

    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
    zell
    -0.07
    uckle
    -0.07
    zza
    -0.07
    ivia
    -0.06
    inka
    -0.06
     kinds
    -0.06
    lessly
    -0.06
    fully
    -0.06
    PILE
    -0.06
    uri
    -0.06
    POSITIVE LOGITS
    _except
    0.07
     surrounding
    0.06
    679
    0.06
    eters
    0.06
    icast
    0.06
    íĺ¹
    0.06
    291
    0.06
    <Option
    0.06
    .tf
    0.06
    ãĥ³ãĥģ
    0.06
    Activations Density 0.051%

    No Known Activations