© 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. 106646
    Prev
    Next
    INDEX
    Explanations

    phrases related to medical diagnostics and patient management

    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
    trl
    -0.06
    ches
    -0.06
    zelf
    -0.06
    bold
    -0.06
     trick
    -0.05
    xs
    -0.05
     Hoover
    -0.05
    ree
    -0.05
    yz
    -0.05
    debian
    -0.05
    POSITIVE LOGITS
    antino
    0.07
    parator
    0.07
     shuffle
    0.07
    ockets
    0.07
    shuffle
    0.07
    ãĤ±ãĥĥãĥĪ
    0.06
    εί
    0.06
    comed
    0.06
    oster
    0.06
    lid
    0.06
    Activations Density 0.001%

    No Known Activations