© 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. 123482
    Prev
    Next
    INDEX
    Explanations

    technical language related to programming and networking, particularly focusing on commands and functions

    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
    cx
    -0.06
    swana
    -0.06
    íļ¨
    -0.06
    ">//
    -0.06
     bott
    -0.06
    ÏĮÏĦη
    -0.06
     trag
    -0.06
    æķĹ
    -0.06
    "&
    -0.06
    unda
    -0.06
    POSITIVE LOGITS
     request
    0.08
     requested
    0.07
    _requested
    0.07
     Request
    0.07
    Requested
    0.07
    znik
    0.07
    uzzi
    0.07
    åij½ä»¤
    0.06
    akin
    0.06
     reply
    0.06
    Activations Density 0.213%

    No Known Activations