© 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. 56590
    Prev
    Next
    INDEX
    Explanations

    specific financial and trading terms

    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
    993
    -0.08
    ancia
    -0.07
    986
    -0.07
    θή
    -0.06
    -0.06
    èįIJ
    -0.06
    isky
    -0.06
    thead
    -0.06
    aggable
    -0.06
    680
    -0.06
    POSITIVE LOGITS
    reas
    0.07
    eah
    0.07
    Îŀ
    0.06
    erin
    0.06
    SDK
    0.06
    ang
    0.06
     Graves
    0.06
     Rück
    0.06
     wis
    0.06
    _sdk
    0.06
    Activations Density 0.017%

    No Known Activations