© 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. 1489
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions and procedures involving the heart and blood vessels

    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
     Morm
    -0.08
    dfs
    -0.08
    ctp
    -0.08
    ycler
    -0.07
    eprom
    -0.07
     Canter
    -0.07
    AGMA
    -0.07
    ernal
    -0.07
    wcs
    -0.07
    ãĥĨãĥ«
    -0.07
    POSITIVE LOGITS
     sizing
    0.07
     poly
    0.06
     wall
    0.06
     hypertension
    0.06
     diameter
    0.06
     strut
    0.06
     left
    0.06
     shepherd
    0.06
    ayas
    0.06
     artery
    0.06
    Activations Density 0.005%

    No Known Activations