© 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. 60285
    Prev
    Next
    INDEX
    Explanations

    terms related to hotel pricing and financial analysis

    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
    ecast
    -0.07
    Lady
    -0.07
     Lady
    -0.07
    timeline
    -0.07
    ocker
    -0.07
    eydi
    -0.06
    ammad
    -0.06
    urdy
    -0.06
     Ecc
    -0.06
    isma
    -0.06
    POSITIVE LOGITS
    èĪ¬
    0.07
     overall
    0.06
     Overall
    0.06
    overall
    0.06
    ocl
    0.06
    782
    0.06
     Mb
    0.06
    /Foundation
    0.06
    Overall
    0.06
    ids
    0.06
    Activations Density 0.001%

    No Known Activations