© 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. 17455
    Prev
    Next
    INDEX
    Explanations

    medical terms and their context within healthcare programs or treatments

    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
     INTERRUPTION
    -0.09
    vla
    -0.07
    oler
    -0.06
     grantResults
    -0.06
    zing
    -0.06
    541
    -0.06
    crypt
    -0.06
    EmptyEntries
    -0.06
    leDb
    -0.06
    edla
    -0.06
    POSITIVE LOGITS
    etc
    0.08
     siz
    0.07
     hatta
    0.07
    ôn
    0.07
     etc
    0.07
     cryst
    0.06
     cÃł
    0.06
    âĢ¦↵↵↵
    0.06
     assorted
    0.06
     ...↵↵↵↵
    0.06
    Activations Density 0.090%

    No Known Activations