© 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. 77609
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical or medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "Clin" appears as part of medical terminology, particularly in words like "clinic," "clinical," or "clinician" in healthcare contexts, medical institutions, research, and professional medical documentation.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    153
    -0.06
    lijke
    -0.06
    ILLE
    -0.06
     requis
    -0.06
    apolis
    -0.06
    ille
    -0.06
    OfType
    -0.06
    ivant
    -0.06
    itur
    -0.06
    yll
    -0.06
    POSITIVE LOGITS
    icians
    0.08
    ician
    0.08
    ãĥ³ãĥĶ
    0.07
    solete
    0.07
    ä¼¼
    0.07
    ipple
    0.07
    sut
    0.07
    iphy
    0.07
    avier
    0.07
    enson
    0.07
    Activations Density 0.009%

    No Known Activations