© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 88527
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-diagnosis and medical advice

    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
    ï¼ľ
    -0.07
     Scaffold
    -0.07
     incel
    -0.06
     Чи
    -0.06
    .Cho
    -0.06
     birinin
    -0.06
    oplan
    -0.06
    ÙĪÙħتر
    -0.06
    urv
    -0.06
    ÙĬدÙĬ
    -0.06
    POSITIVE LOGITS
     medical
    0.09
     diagnostic
    0.09
     diagnostics
    0.08
     diagnosis
    0.08
    -di
    0.08
    medical
    0.08
     diagnose
    0.08
    iagnostics
    0.07
     synd
    0.07
     diag
    0.07
    Activations Density 0.012%

    No Known Activations