© 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. 26709
    Prev
    Next
    INDEX
    Explanations

    economic terms related to currency value and trade

    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
     tap
    -0.06
     harness
    -0.06
     foundation
    -0.06
     smooth
    -0.06
     assoc
    -0.06
    angan
    -0.06
     cul
    -0.06
     tapping
    -0.06
    evin
    -0.06
    otte
    -0.06
    POSITIVE LOGITS
    ãĥ¥ãĥ¼
    0.07
    å¢ĥ
    0.07
    طار
    0.06
    roat
    0.06
    éry
    0.06
    flation
    0.06
    岸
    0.06
     Bun
    0.06
    TRY
    0.06
    окÑĥ
    0.06
    Activations Density 0.026%

    No Known Activations