© 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 EvalsExportsinterp-engineNEWAPI 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. 98656
    Prev
    Next
    INDEX
    Explanations

    mentions of the Sputnik V COVID-19 vaccine and its effectiveness

    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
    ayscale
    -0.07
    hir
    -0.07
     hire
    -0.07
    amage
    -0.07
    UBL
    -0.07
     permalink
    -0.07
    ilogue
    -0.06
     thuê
    -0.06
    .scalablytyped
    -0.06
    ertain
    -0.06
    POSITIVE LOGITS
    emann
    0.07
    Ñİдж
    0.07
     variant
    0.06
     immature
    0.06
     promising
    0.06
     Naz
    0.06
    291
    0.06
    arily
    0.06
     slack
    0.06
     du
    0.06
    Activations Density 0.005%

    No Known Activations