© 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. 17-LLAMASCOPE-RES-131K
    11. 58249
    Prev
    Next
    INDEX
    Explanations

    references to vaccines and their effects

    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
     Hra
    -0.08
    SPA
    -0.07
     zas
    -0.07
    yte
    -0.07
     Probe
    -0.07
    tal
    -0.07
    .party
    -0.06
    /fw
    -0.06
    Ùİت
    -0.06
    OrFail
    -0.06
    POSITIVE LOGITS
     safety
    0.07
    ocard
    0.07
     experimental
    0.06
     temper
    0.06
     side
    0.06
    experimental
    0.06
     mRNA
    0.06
    347
    0.06
     safest
    0.06
     TEM
    0.06
    Activations Density 0.012%

    No Known Activations