© 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. 106561
    Prev
    Next
    INDEX
    Explanations

    discussions on financial assistance and loan repayment programs for medical professionals

    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
    eteria
    -0.08
    CI
    -0.07
    ê°IJ
    -0.07
    à¸ģำ
    -0.07
    /Instruction
    -0.07
    æ¢
    -0.07
    iero
    -0.07
    icable
    -0.07
    ourt
    -0.07
    strand
    -0.07
    POSITIVE LOGITS
     MD
    0.08
     Dr
    0.08
     physician
    0.08
     practicing
    0.08
     dr
    0.07
    amed
    0.07
     gastro
    0.07
     AMA
    0.07
     medical
    0.07
     specialties
    0.07
    Activations Density 0.206%

    No Known Activations