© 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. 56318
    Prev
    Next
    INDEX
    Explanations

    terms associated with global financial markets and their dynamics

    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
    kart
    -0.07
    urch
    -0.07
    aller
    -0.06
    olet
    -0.06
    /assert
    -0.06
    ãĥĥãĥī
    -0.06
    alla
    -0.06
    ella
    -0.06
    egasus
    -0.06
    escal
    -0.06
    POSITIVE LOGITS
     hosting
    0.07
     hosted
    0.07
     attract
    0.07
     رÙĤ
    0.07
    forum
    0.07
    ÑģÑĭ
    0.06
     hub
    0.06
    857
    0.06
    ystack
    0.06
     destination
    0.06
    Activations Density 0.037%

    No Known Activations