© 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. 26839
    Prev
    Next
    INDEX
    Explanations

    terms related to manufacturing processes and materials

    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
    kili
    -0.07
    絶
    -0.06
     Thiên
    -0.06
    bos
    -0.06
     ÐľÑĸж
    -0.06
     Appalachian
    -0.06
     Fog
    -0.06
    afia
    -0.06
     crisis
    -0.06
     Defensive
    -0.06
    POSITIVE LOGITS
     casting
    0.09
     Casting
    0.07
    icast
    0.07
    endale
    0.07
     cast
    0.07
    _cast
    0.07
    acimiento
    0.07
     casts
    0.07
     caster
    0.07
    cast
    0.07
    Activations Density 0.007%

    No Known Activations