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

    Neuronpedia

    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. 41110
    Prev
    Next
    INDEX
    Explanations

    medical terms and references related to physiological conditions and indicators

    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
     VÅ¡ech
    -0.09
    onto
    -0.08
    quia
    -0.08
    reur
    -0.08
     promin
    -0.08
    _escape
    -0.07
    .debian
    -0.07
     addCriterion
    -0.07
    PLATFORM
    -0.07
     плав
    -0.07
    POSITIVE LOGITS
     status
    0.09
     presence
    0.07
     potential
    0.07
     disease
    0.07
     actively
    0.06
    status
    0.06
     activity
    0.06
     active
    0.06
     underlying
    0.06
     progress
    0.06
    Activations Density 0.026%

    No Known Activations