© 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. 124552
    Prev
    Next
    INDEX
    Explanations

    financial terms related to cash flow and balance sheets

    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
    urch
    -0.07
     ============================================================================↵
    -0.07
    uard
    -0.07
    elho
    -0.07
    kle
    -0.07
    tml
    -0.07
    DMI
    -0.07
    imdi
    -0.07
    .nano
    -0.07
     putas
    -0.07
    POSITIVE LOGITS
     held
    0.07
     reserves
    0.07
     ready
    0.06
    ready
    0.06
     remaining
    0.06
     collar
    0.06
     readily
    0.06
     cushion
    0.06
    -collar
    0.06
     holding
    0.06
    Activations Density 0.009%

    No Known Activations