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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3419
    Prev
    Next
    INDEX
    Explanations

    references to external influences on markets and economies

    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
     Uncomment
    -0.07
    à¸Ķย
    -0.07
     representative
    -0.07
    annes
    -0.07
     Ä°nsan
    -0.06
    quiv
    -0.06
     tö
    -0.06
    γκα
    -0.06
    .interfaces
    -0.06
    ادة
    -0.06
    POSITIVE LOGITS
    Macro
    0.09
    macro
    0.09
     factors
    0.09
     macro
    0.07
    ách
    0.07
    Drivers
    0.07
     circumstances
    0.07
     drivers
    0.07
     ÑĦакÑĤоÑĢ
    0.07
     Factors
    0.07
    Activations Density 0.045%

    No Known Activations