© 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. 18598
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical failure and vehicle performance

    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
    ä»·
    -0.06
    addons
    -0.06
    azel
    -0.06
    .Utc
    -0.06
    ettes
    -0.06
    _mini
    -0.06
    TimeString
    -0.06
     tinh
    -0.06
    alli
    -0.06
    ospace
    -0.06
    POSITIVE LOGITS
    unch
    0.08
     worn
    0.08
    merce
    0.07
     wear
    0.07
     Blob
    0.06
     vým
    0.06
    ÐĤ
    0.06
    astro
    0.06
    Exp
    0.06
     punct
    0.06
    Activations Density 0.000%

    No Known Activations