© 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. 89770
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to various types of products and their applications

    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
    antz
    -0.07
    aign
    -0.06
     util
    -0.06
     th
    -0.06
    iston
    -0.06
    obec
    -0.06
    awan
    -0.06
     Kamp
    -0.06
     ROC
    -0.06
    onas
    -0.06
    POSITIVE LOGITS
    çĶ¨çļĦ
    0.09
    ìļ©
    0.08
    indered
    0.07
    olest
    0.07
    ponde
    0.07
    apia
    0.07
     Needs
    0.07
     addCriterion
    0.07
    leftright
    0.07
    -prepend
    0.07
    Activations Density 0.038%

    No Known Activations