© 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. 116342
    Prev
    Next
    INDEX
    Explanations

    words related to craftsmanship and quality 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
     Moderate
    -0.07
    ettel
    -0.07
     Woodward
    -0.07
    etler
    -0.07
    icer
    -0.07
    oda
    -0.07
    ozem
    -0.07
    asca
    -0.07
    eil
    -0.07
    enz
    -0.06
    POSITIVE LOGITS
    ẩm
    0.06
     traded
    0.06
    Layers
    0.06
    _layers
    0.06
     Theodore
    0.06
    -yellow
    0.06
     facto
    0.06
     altına
    0.05
     imp
    0.05
     bands
    0.05
    Activations Density 0.000%

    No Known Activations