© 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. 116374
    Prev
    Next
    INDEX
    Explanations

    technical terminology and details related to plasma flow modeling in scientific contexts

    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
    798
    -0.06
    gypt
    -0.06
     Heat
    -0.06
    _lift
    -0.06
    881
    -0.06
    867
    -0.06
    erator
    -0.06
    eler
    -0.05
    رد
    -0.05
    bows
    -0.05
    POSITIVE LOGITS
    FLASH
    0.08
     Ulus
    0.08
    cone
    0.07
    _flash
    0.07
     flash
    0.07
    kov
    0.07
    BSD
    0.07
     FLASH
    0.07
     Ãĸzel
    0.07
    -flash
    0.07
    Activations Density 0.031%

    No Known Activations