© 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. 9-LLAMASCOPE-RES-131K
    11. 95834
    Prev
    Next
    INDEX
    Explanations

    references to hospital beds and related capacity issues in healthcare

    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
    znik
    -0.06
    çıį
    -0.06
    671
    -0.06
     cumulative
    -0.06
    oÄŁ
    -0.06
    /us
    -0.06
     Dudley
    -0.06
    ander
    -0.06
    ceb
    -0.06
    UMB
    -0.06
    POSITIVE LOGITS
     StringComparison
    0.06
    æĸ½
    0.06
    plus
    0.06
    abic
    0.06
     ve
    0.06
    isma
    0.06
     BaseModel
    0.06
    nu
    0.06
     Herman
    0.06
    ائÙĤ
    0.06
    Activations Density 0.003%

    No Known Activations