© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42793
    Prev
    Next
    INDEX
    Explanations

    information related to vaccine efficacy and COVID-19

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    FRING
    -0.07
    erif
    -0.07
    شت
    -0.06
    شتÙĩ
    -0.06
     Relief
    -0.06
    utin
    -0.06
    Ð¡Ðł
    -0.06
    AINS
    -0.06
    ãĥ¼ãĥ³
    -0.06
    UNS
    -0.06
    POSITIVE LOGITS
     trial
    0.08
     Thom
    0.06
     Robbins
    0.06
    /tos
    0.06
    eth
    0.06
    udi
    0.06
     trials
    0.06
    els
    0.06
    eldon
    0.06
     participant
    0.06
    Activations Density 0.004%

    No Known Activations