© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75900
    Prev
    Next
    INDEX
    Explanations

    financial terms related to interest rates and market fluctuations

    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
    .reducer
    -0.07
     Drill
    -0.07
    ModelState
    -0.07
    .dimension
    -0.07
    ingham
    -0.07
     зг
    -0.07
    kir
    -0.07
    union
    -0.07
     frais
    -0.07
    andre
    -0.07
    POSITIVE LOGITS
    .gov
    0.07
    iero
    0.06
     kür
    0.06
    stroy
    0.06
    ados
    0.06
    elix
    0.06
    ledged
    0.05
     con
    0.05
    olesale
    0.05
    fed
    0.05
    Activations Density 0.001%

    No Known Activations