© 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. 77644
    Prev
    Next
    INDEX
    Explanations

    references to cleaning and maintenance procedures involving materials and equipment

    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
    .po
    -0.07
    pac
    -0.06
    allery
    -0.06
    gang
    -0.06
    iej
    -0.06
    chop
    -0.06
    yme
    -0.06
    achinery
    -0.06
    [Double
    -0.06
    одаÑĢ
    -0.06
    POSITIVE LOGITS
     dust
    0.09
     dry
    0.08
     Dust
    0.08
    cki
    0.07
    dust
    0.07
     Dry
    0.06
     Nano
    0.06
    ULA
    0.06
    Align
    0.06
    uci
    0.06
    Activations Density 0.013%

    No Known Activations