© 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. 125633
    Prev
    Next
    INDEX
    Explanations

    references to intensive care units (ICUs) and neonatal intensive care units (NICUs)

    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
    μη
    -0.08
    lehem
    -0.08
    _CAN
    -0.07
    .future
    -0.07
     Eag
    -0.07
    omite
    -0.07
    Extent
    -0.07
     gá»ijc
    -0.07
    .ud
    -0.07
    μά
    -0.07
    POSITIVE LOGITS
    860
    0.06
     unit
    0.06
    bers
    0.06
    304
    0.06
    aving
    0.06
     beds
    0.06
     located
    0.06
    1
    0.06
     se
    0.06
     admitting
    0.06
    Activations Density 0.007%

    No Known Activations