© 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. 73476
    Prev
    Next
    INDEX
    Explanations

    key terms related to market trends and pricing

    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
     workforce
    -0.06
    aska
    -0.06
    716
    -0.05
    uter
    -0.05
     tenant
    -0.05
     subsequ
    -0.05
     asynchronously
    -0.05
     fitness
    -0.05
     urban
    -0.05
     voice
    -0.05
    POSITIVE LOGITS
     auction
    0.08
    .easy
    0.08
    erver
    0.08
    auction
    0.07
    _repr
    0.07
     prices
    0.07
    .rep
    0.07
    DCF
    0.07
     Constantin
    0.07
    prices
    0.07
    Activations Density 0.004%

    No Known Activations