© 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. 89494
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and methods

    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
     Ying
    -0.07
    EDA
    -0.06
     Bi
    -0.06
     bi
    -0.05
     eks
    -0.05
    t
    -0.05
    IFT
    -0.05
     groceries
    -0.05
    eda
    -0.05
    otta
    -0.05
    POSITIVE LOGITS
     rehe
    0.08
    ovacÃŃ
    0.08
    -serving
    0.08
    湯
    0.08
    quam
    0.08
    frauen
    0.07
    utters
    0.07
    forman
    0.07
    piler
    0.07
    steam
    0.07
    Activations Density 0.061%

    No Known Activations