© 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. 75849
    Prev
    Next
    INDEX
    Explanations

    terms related to stem cell research and their applications

    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
    ç¼
    -0.07
    ä¼ģ
    -0.07
    aco
    -0.07
    .zh
    -0.06
    unte
    -0.06
    ned
    -0.06
    coli
    -0.06
    ugged
    -0.06
    strand
    -0.06
    nels
    -0.06
    POSITIVE LOGITS
    itler
    0.07
     Tk
    0.06
     cells
    0.06
     Shah
    0.06
    -cell
    0.06
    ARS
    0.06
    idla
    0.06
     Uhr
    0.06
    -desc
    0.06
    ery
    0.06
    Activations Density 0.009%

    No Known Activations