© 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. 78337
    Prev
    Next
    INDEX
    Explanations

    references to academic institutions and their associated materials or guidelines

    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
    æĻ
    -0.07
    cek
    -0.07
     Loy
    -0.07
    åIJ
    -0.06
    ablish
    -0.06
     bin
    -0.06
    Ä°T
    -0.06
    zel
    -0.06
    brook
    -0.06
    izable
    -0.06
    POSITIVE LOGITS
     understanding
    0.07
    unte
    0.07
     How
    0.07
    onest
    0.07
    ureau
    0.07
     how
    0.07
     Why
    0.06
    ynet
    0.06
     why
    0.06
     Understanding
    0.06
    Activations Density 0.012%

    No Known Activations