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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 118416
    Prev
    Next
    INDEX
    Explanations

    terms related to healthcare, particularly in emergency situations and access to medical services

    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
    geber
    -0.07
    ãĤ¤ãĤ¯
    -0.07
     iÅŁ
    -0.07
    veis
    -0.07
    лки
    -0.07
    atik
    -0.07
    ucs
    -0.07
    é¤IJ
    -0.07
    ови
    -0.07
     lã
    -0.07
    POSITIVE LOGITS
     medical
    0.14
     treatment
    0.13
     treatments
    0.12
     Medical
    0.11
    medical
    0.11
     Treatment
    0.10
    Medical
    0.10
     doctor
    0.10
     healthcare
    0.10
     treated
    0.09
    Activations Density 0.196%

    No Known Activations