© 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. 54055
    Prev
    Next
    INDEX
    Explanations

    mentions of vaccine-related discussions and approvals

    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
    alore
    -0.08
    ãĥ³ãĥĨ
    -0.07
    xis
    -0.06
    pcf
    -0.06
    Lv
    -0.06
    grams
    -0.06
    nant
    -0.06
     Lv
    -0.06
    .Automation
    -0.06
    zell
    -0.06
    POSITIVE LOGITS
     remot
    0.06
    oste
    0.06
     =$
    0.06
     @(
    0.05
     wage
    0.05
    ÅĻe
    0.05
    argar
    0.05
     ë²½
    0.05
     VK
    0.05
     Dag
    0.05
    Activations Density 0.011%

    No Known Activations