© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 116525
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures and their specifics

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    å¹
    -0.07
    andi
    -0.07
    .scalablytyped
    -0.06
    indered
    -0.06
    aising
    -0.06
    adam
    -0.06
     nhẹ
    -0.06
    oller
    -0.06
     jist
    -0.06
     insignificant
    -0.06
    POSITIVE LOGITS
     often
    0.09
    often
    0.08
     require
    0.08
     costly
    0.08
     must
    0.07
     requires
    0.07
     expensive
    0.07
    REQUIRED
    0.07
    Requires
    0.07
     typically
    0.07
    Activations Density 0.019%

    No Known Activations