© 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. 128403
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to cardiac procedures and conditions

    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
    vu
    -0.07
    ucht
    -0.07
     Rift
    -0.06
    å¼±
    -0.06
     Nem
    -0.06
     má
    -0.06
    Kn
    -0.06
    728
    -0.06
     á
    -0.06
    mb
    -0.06
    POSITIVE LOGITS
    arcy
    0.08
    ardown
    0.07
    ipse
    0.07
    ledik
    0.07
    æ°¸ä¹ħ
    0.07
     problems
    0.07
    ivot
    0.07
     Pace
    0.07
    avax
    0.06
    æĿIJ
    0.06
    Activations Density 0.008%

    No Known Activations