© 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. 61699
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to health statistics and COVID-19 cases

    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
    ubl
    -0.08
    ovnÃŃ
    -0.07
    ereo
    -0.07
    EIF
    -0.07
    kaar
    -0.07
    ERE
    -0.07
    kip
    -0.07
    oblin
    -0.06
    ere
    -0.06
    afb
    -0.06
    POSITIVE LOGITS
     Sew
    0.07
    PCR
    0.06
     Floating
    0.06
    éĻ½
    0.06
    TestMethod
    0.06
     Hos
    0.06
     Delta
    0.06
     Vari
    0.06
     Om
    0.06
    ави
    0.06
    Activations Density 0.010%

    No Known Activations