© 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. 31741
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to engineering or physical processes

    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
    emark
    -0.07
    Ascii
    -0.07
    essim
    -0.07
    ungan
    -0.07
    plx
    -0.06
     LÃłm
    -0.06
    /bower
    -0.06
    ãĥ³ãĥĩãĤ£
    -0.06
     mạch
    -0.06
    ìī¬
    -0.06
    POSITIVE LOGITS
     sometimes
    0.10
    sometimes
    0.07
    may
    0.07
     Sometimes
    0.07
    Sometimes
    0.07
     often
    0.07
     examples
    0.07
     may
    0.07
     modern
    0.06
     generally
    0.06
    Activations Density 0.030%

    No Known Activations