© 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. 85556
    Prev
    Next
    INDEX
    Explanations

    concepts related to public health programs and pandemic preparedness

    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
     ===>
    -0.08
    istine
    -0.07
    inÄĽ
    -0.07
     dair
    -0.07
    clidean
    -0.07
    ále
    -0.07
    olie
    -0.06
    éry
    -0.06
    bsd
    -0.06
    rends
    -0.06
    POSITIVE LOGITS
     Prepared
    0.08
     prepared
    0.08
    prepared
    0.07
     world
    0.07
    ande
    0.07
     ä¸ĸ
    0.06
     davon
    0.06
     focal
    0.06
     Trad
    0.06
    Emer
    0.06
    Activations Density 0.006%

    No Known Activations