© 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. 75851
    Prev
    Next
    INDEX
    Explanations

    terms related to cell growth, apoptosis, and the mechanisms affecting these processes

    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
     Bil
    -0.08
     bilin
    -0.07
     bilateral
    -0.07
    lectron
    -0.06
    enso
    -0.06
     Ernest
    -0.06
     NotImplemented
    -0.06
     gast
    -0.06
     bil
    -0.06
    uga
    -0.06
    POSITIVE LOGITS
     cell
    0.11
     cells
    0.10
     Cell
    0.09
     prolifer
    0.09
     Cells
    0.09
     proliferation
    0.09
    cell
    0.09
    Cell
    0.08
    ç»Ĩèĥŀ
    0.08
    .cell
    0.07
    Activations Density 0.029%

    No Known Activations