Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 56150
    Prev
    Next
    INDEX
    Explanations

    references to financial and governance-related topics

    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
    OLDER
    -0.07
    ASURE
    -0.07
    /wiki
    -0.07
     datings
    -0.07
    ÙıÙĪØ§
    -0.07
    رخ
    -0.07
    _icall
    -0.07
    REEN
    -0.07
    Subview
    -0.07
    à¸ķรà¸ĩ
    -0.07
    POSITIVE LOGITS
    Conclusion
    0.14
     conclusion
    0.14
     future
    0.13
     Conclusion
    0.13
     conclude
    0.12
     concluding
    0.12
     concludes
    0.11
     final
    0.10
     conclusions
    0.09
     concluded
    0.09
    Activations Density 0.014%

    No Known Activations