© 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 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. 17-LLAMASCOPE-RES-131K
    11. 76533
    Prev
    Next
    INDEX
    Explanations

    monetary values and financial transactions

    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
     Gut
    -0.06
     Reyn
    -0.06
    erken
    -0.06
    má
    -0.06
    ordova
    -0.06
     wash
    -0.06
     Giul
    -0.06
     Sant
    -0.06
     station
    -0.06
     guar
    -0.06
    POSITIVE LOGITS
     Software
    0.07
     cloud
    0.07
    rica
    0.06
     foss
    0.06
     reign
    0.06
    alo
    0.06
    lane
    0.06
    Cloud
    0.06
     software
    0.06
    alance
    0.06
    Activations Density 0.010%

    No Known Activations