© 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. 118936
    Prev
    Next
    INDEX
    Explanations

    references to currency manipulation and trade competitiveness

    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
    eza
    -0.07
    oyal
    -0.07
    odia
    -0.07
    bett
    -0.07
     rede
    -0.07
    akh
    -0.06
    icari
    -0.06
    phis
    -0.06
    mployee
    -0.06
    culo
    -0.06
    POSITIVE LOGITS
     specialization
    0.07
     exchange
    0.07
     Exchange
    0.07
    iki
    0.07
     trade
    0.07
     production
    0.07
     '..',
    0.06
    unde
    0.06
    -trade
    0.06
     Production
    0.06
    Activations Density 0.001%

    No Known Activations