© 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. 1531
    Prev
    Next
    INDEX
    Explanations

    references to software and related documentation

    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
    oeff
    -0.08
    otte
    -0.08
    okino
    -0.07
    otron
    -0.07
    úi
    -0.07
    ¢åįķ
    -0.07
    ssp
    -0.07
    ako
    -0.07
    azon
    -0.07
    ombine
    -0.06
    POSITIVE LOGITS
     Woodward
    0.07
     sho
    0.06
    UES
    0.06
    .sendStatus
    0.06
    ASE
    0.06
    gtest
    0.06
    IED
    0.05
     Laud
    0.05
    -slide
    0.05
    лÑıв
    0.05
    Activations Density 0.001%

    No Known Activations