© 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. 30341
    Prev
    Next
    INDEX
    Explanations

    financial terminology and numeric values related to accounting and payments

    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
    urat
    -0.09
     Latter
    -0.07
    uracy
    -0.07
    isku
    -0.07
    _sta
    -0.07
    ieu
    -0.07
    õi
    -0.07
    .Encoding
    -0.07
    ureau
    -0.06
    agas
    -0.06
    POSITIVE LOGITS
     because
    0.07
     total
    0.06
    because
    0.06
     Scenario
    0.06
     McGregor
    0.06
     unprotected
    0.06
     Looks
    0.05
     consum
    0.05
     Total
    0.05
     ÃĹ
    0.05
    Activations Density 0.011%

    No Known Activations