© 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. 14348
    Prev
    Next
    INDEX
    Explanations

    medical terms associated with cardiac procedures and conditions

    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
    beros
    -0.09
     InitializeComponent
    -0.08
    ZeroWidthSpace
    -0.07
    berman
    -0.07
    #
    -0.07
    antal
    -0.07
    phin
    -0.07
    ERA
    -0.07
    çģµ
    -0.07
    ngth
    -0.07
    POSITIVE LOGITS
    ÙĪدÙĩ
    0.06
    216
    0.06
     di
    0.06
     charts
    0.06
     legion
    0.06
     coils
    0.06
     ac
    0.06
     x
    0.05
     X
    0.05
     thereafter
    0.05
    Activations Density 0.005%

    No Known Activations