© 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. 86616
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to medical imaging, particularly MRI and cardiovascular procedures

    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
    ầm
    -0.07
    اÙĨÚ¯
    -0.06
    argin
    -0.06
     scrape
    -0.06
     Solar
    -0.06
     solar
    -0.06
    æİĮ
    -0.06
    hea
    -0.06
    ROUGH
    -0.06
     digestion
    -0.06
    POSITIVE LOGITS
     imaging
    0.10
     Gad
    0.08
     MRI
    0.08
     Imaging
    0.08
    .spin
    0.08
    MRI
    0.07
     magnetic
    0.07
    echo
    0.07
     Magnetic
    0.07
    -images
    0.07
    Activations Density 0.008%

    No Known Activations