© 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 EvalsExportsinterp-engineNEWAPI 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. 95062
    Prev
    Next
    INDEX
    Explanations

    terms related to medical and health professions

    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
     )↵↵↵↵↵↵↵↵
    -0.08
    íĹĮ
    -0.08
    ãĤħ
    -0.08
    Gtk
    -0.07
    rica
    -0.07
    ,eg
    -0.07
    icode
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
     defaultManager
    -0.07
     ober
    -0.07
    POSITIVE LOGITS
    328
    0.06
    èĻ
    0.06
     Feld
    0.06
    ziej
    0.06
    zenia
    0.05
    rians
    0.05
    ument
    0.05
    logging
    0.05
    ¬¬
    0.05
    827
    0.05
    Activations Density 0.040%

    No Known Activations