© 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. 15-LLAMASCOPE-RES-131K
    11. 103493
    Prev
    Next
    INDEX
    Explanations

    quantitative measures and significant numerical trends in financial contexts

    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
    afc
    -0.07
    quartered
    -0.07
    боÑĢа
    -0.07
    kova
    -0.07
     Pron
    -0.07
    ahren
    -0.06
    ÅŁtır
    -0.06
    %B
    -0.06
    INLINE
    -0.06
    >({
    -0.06
    POSITIVE LOGITS
    aye
    0.06
    agen
    0.06
    _builder
    0.06
    æĹ¥ãģ®
    0.06
     Builder
    0.06
    ãģ£ãģ¡
    0.06
     antig
    0.06
    /includes
    0.06
    GES
    0.06
     æĻ
    0.06
    Activations Density 0.002%

    No Known Activations