© 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. 108585
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatment and healthcare policies

    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
    nete
    -0.08
    auga
    -0.07
    uchos
    -0.07
    slaught
    -0.07
    ieux
    -0.07
    aux
    -0.07
    issional
    -0.07
    ycin
    -0.07
    adata
    -0.07
    .lift
    -0.07
    POSITIVE LOGITS
     emergency
    0.07
     rescue
    0.07
     antid
    0.07
     throwable
    0.06
     available
    0.06
     revers
    0.06
     breath
    0.06
     amb
    0.06
     resc
    0.06
    apid
    0.06
    Activations Density 0.002%

    No Known Activations