© 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. 69171
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "os" related to operating system functionality in code

    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
    theless
    -0.07
    cott
    -0.07
    redo
    -0.07
    egers
    -0.07
    to
    -0.06
    imon
    -0.06
    ite
    -0.06
    ebb
    -0.06
    ously
    -0.06
    isper
    -0.06
    POSITIVE LOGITS
    bote
    0.07
    alic
    0.07
    vore
    0.07
    .scalablytyped
    0.07
    ctest
    0.07
    bern
    0.07
    itivity
    0.07
    abin
    0.07
    vit
    0.07
    CAF
    0.07
    Activations Density 0.001%

    No Known Activations