© 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. 4616
    Prev
    Next
    INDEX
    Explanations

    financial ratios and metrics related to capital efficiency and performance

    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
    ิà¸Ļà¸Ķ
    -0.08
    urum
    -0.07
    coni
    -0.07
    rawer
    -0.07
    oux
    -0.07
    iyah
    -0.07
    мп
    -0.07
    OUS
    -0.07
    estro
    -0.07
     tradi
    -0.07
    POSITIVE LOGITS
     Nas
    0.06
     Sachs
    0.06
     TL
    0.06
    iverse
    0.06
     shareholders
    0.06
    _plural
    0.05
    íħ
    0.05
     Frankie
    0.05
     harmon
    0.05
     continental
    0.05
    Activations Density 0.002%

    No Known Activations