© 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 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. 17-LLAMASCOPE-RES-131K
    11. 29183
    Prev
    Next
    INDEX
    Explanations

    concepts related to duality and the interplay between opposing forces

    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
    azzi
    -0.07
    jsc
    -0.07
    icode
    -0.06
    寿
    -0.06
    aoke
    -0.06
    omid
    -0.06
    omik
    -0.06
    sak
    -0.06
     departed
    -0.06
    cot
    -0.06
    POSITIVE LOGITS
     balance
    0.10
     Yin
    0.10
    Balance
    0.09
    balance
    0.09
     Balance
    0.09
     balances
    0.08
     balanced
    0.08
     complementary
    0.08
    balances
    0.07
     extremes
    0.07
    Activations Density 0.040%

    No Known Activations