© 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. 63278
    Prev
    Next
    INDEX
    Explanations

    keywords related to inventory management and operational 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
    922
    -0.07
    sizeof
    -0.07
    abcdefghijklmnop
    -0.06
    lord
    -0.06
    appa
    -0.06
    kou
    -0.06
     Kurt
    -0.06
     contours
    -0.06
    tual
    -0.06
    oints
    -0.06
    POSITIVE LOGITS
    ToFront
    0.07
    @brief
    0.07
    quist
    0.07
    ιÏĥμÏĮÏĤ
    0.07
    /tab
    0.07
    -toast
    0.06
    _tac
    0.06
    ÙĨز
    0.06
     yat
    0.06
     outr
    0.06
    Activations Density 0.006%

    No Known Activations