© 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. 96148
    Prev
    Next
    INDEX
    Explanations

    topics related to outdoor shade and shelter solutions

    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
    ÏĥÏĨ
    -0.07
    lak
    -0.07
    erras
    -0.06
    pus
    -0.06
    porter
    -0.06
    ean
    -0.06
    alte
    -0.06
    eyse
    -0.06
    zÃŃ
    -0.06
    scrollTop
    -0.06
    POSITIVE LOGITS
     Consort
    0.06
     sensitive
    0.06
    å¯
    0.06
     users
    0.06
     ÙĨسÙħØ©
    0.06
    inand
    0.06
    èĶµ
    0.06
     COPYRIGHT
    0.06
    UX
    0.06
     otherwise
    0.06
    Activations Density 0.023%

    No Known Activations