© 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. 17-LLAMASCOPE-RES-131K
    11. 83451
    Prev
    Next
    INDEX
    Explanations

    references to gymnastics and affiliated terms

    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
    ño
    -0.08
    ارج
    -0.07
    ftime
    -0.07
    igator
    -0.07
    lda
    -0.07
    ÑĥлÑİ
    -0.07
    hsi
    -0.07
    iag
    -0.07
    elop
    -0.07
    rag
    -0.07
    POSITIVE LOGITS
     Vaults
    0.07
     bare
    0.06
    olds
    0.06
     vault
    0.06
     Posting
    0.06
    466
    0.06
     gymn
    0.06
     Samar
    0.05
    piration
    0.05
    bare
    0.05
    Activations Density 0.006%

    No Known Activations