© 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. 129871
    Prev
    Next
    INDEX
    Explanations

    mentions of global and international markets or industries

    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
    ãĥĸãĥª
    -0.08
    ongyang
    -0.07
     Lal
    -0.07
    istik
    -0.07
    екÑĤи
    -0.06
    üzel
    -0.06
    croft
    -0.06
    etch
    -0.06
    wo
    -0.06
    ibri
    -0.06
    POSITIVE LOGITS
     market
    0.17
     markets
    0.13
    market
    0.12
    å¸Ĥåľº
    0.12
    å¸Ĥåł´
    0.12
     marketplace
    0.11
     Market
    0.11
    .market
    0.10
     scene
    0.09
    -market
    0.09
    Activations Density 0.034%

    No Known Activations