© 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. 59444
    Prev
    Next
    INDEX
    Explanations

    terms related to swine flu and its impact

    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
     covid
    -0.08
    lsen
    -0.07
    toi
    -0.07
    .scalablytyped
    -0.07
    202
    -0.06
    COVID
    -0.06
     COVID
    -0.06
    lei
    -0.06
     Covid
    -0.06
     Patreon
    -0.06
    POSITIVE LOGITS
     stocks
    0.06
     mass
    0.06
    seealso
    0.06
    wich
    0.06
    orra
    0.06
     emergency
    0.06
    stocks
    0.06
    etsk
    0.06
    declspec
    0.06
     stock
    0.06
    Activations Density 0.008%

    No Known Activations