© 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 EvalsExportsinterp-engineNEWAPI 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. 79484
    Prev
    Next
    INDEX
    Explanations

    terms related to cellular processes and organization

    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
    311
    -0.07
    sector
    -0.06
    qp
    -0.06
    arena
    -0.06
    archical
    -0.06
    ä¼ı
    -0.06
    Ìī
    -0.06
    lor
    -0.06
    lops
    -0.06
    _PKT
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.11
     motivation
    0.07
    owan
    0.07
     why
    0.07
    chwitz
    0.06
    lanma
    0.06
    unix
    0.06
     Song
    0.06
    rollo
    0.06
    ãĥĥãĤ°
    0.06
    Activations Density 0.059%

    No Known Activations