© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 81374
    Prev
    Next
    INDEX
    Explanations

    terms related to 3D printing and its materials

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ograd
    -0.07
    estre
    -0.07
     smear
    -0.07
    ORIZ
    -0.07
    lags
    -0.06
     abstraction
    -0.06
     stripe
    -0.06
     маз
    -0.06
    witch
    -0.06
    Pixmap
    -0.06
    POSITIVE LOGITS
     plu
    0.07
     Merk
    0.07
    istrovstvÃŃ
    0.07
    multipart
    0.06
    Ki
    0.06
    imbledon
    0.06
    hack
    0.06
     Exploration
    0.06
     STL
    0.06
    imensional
    0.06
    Activations Density 0.017%

    No Known Activations