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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2394
    Prev
    Next
    INDEX
    Explanations

    references to digital currencies and their implications in international finance

    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
    ãĥ¬ãĥĥãĥĪ
    -0.07
     âĢª
    -0.07
     Redistributions
    -0.07
    รà¸ĵ
    -0.07
    asts
    -0.07
    .::
    -0.07
    eel
    -0.07
    ãĥ³ãĥĦ
    -0.06
    ogie
    -0.06
    levision
    -0.06
    POSITIVE LOGITS
     digit
    0.08
     digital
    0.07
     circ
    0.07
     Iss
    0.07
     issued
    0.07
     circulated
    0.07
    issued
    0.06
     pilot
    0.06
     gram
    0.06
    737
    0.06
    Activations Density 0.008%

    No Known Activations