© 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. 15-LLAMASCOPE-RES-131K
    11. 61288
    Prev
    Next
    INDEX
    Explanations

    concepts related to medical events and diagnoses

    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
    æī§
    -0.06
    åĢĴ
    -0.06
    Z
    -0.06
     lie
    -0.05
     Cush
    -0.05
    olf
    -0.05
    .visual
    -0.05
     Knock
    -0.05
     leadership
    -0.05
     impl
    -0.05
    POSITIVE LOGITS
    HeaderCode
    0.09
    OptionsResolver
    0.08
    ynos
    0.08
    PyObject
    0.07
    izon
    0.07
     докÑĥм
    0.07
    ument
    0.07
    StandardItem
    0.07
     seedu
    0.07
    RuntimeObject
    0.07
    Activations Density 0.004%

    No Known Activations