© 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 EvalsExportsAPI 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. 78525
    Prev
    Next
    INDEX
    Explanations

    references to insurance and related concepts

    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
    .scalablytyped
    -0.08
    uum
    -0.07
     ì¶ľìŀ¥
    -0.07
    iage
    -0.07
    .oc
    -0.07
    sst
    -0.07
    dock
    -0.07
    odef
    -0.07
    æĬĺ
    -0.07
    sage
    -0.07
    POSITIVE LOGITS
     life
    0.07
     Coverage
    0.07
     Life
    0.07
     coverage
    0.06
    Coverage
    0.06
     death
    0.06
    atz
    0.06
     TERM
    0.06
     Span
    0.06
     Sel
    0.06
    Activations Density 0.001%

    No Known Activations