© 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. 107584
    Prev
    Next
    INDEX
    Explanations

    terms related to vaccine boosters and vaccinations

    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
    Unsigned
    -0.08
    PageIndex
    -0.07
    çī
    -0.07
    Č↵
    -0.07
     embry
    -0.07
    ELLOW
    -0.07
    raci
    -0.07
    çŃĴ
    -0.06
    رÙĬÙħ
    -0.06
    ersist
    -0.06
    POSITIVE LOGITS
     booster
    0.06
     boost
    0.06
    esty
    0.06
     available
    0.06
    _LOGGER
    0.05
    uish
    0.05
    .jupiter
    0.05
     BOOST
    0.05
     RT
    0.05
     additional
    0.05
    Activations Density 0.003%

    No Known Activations