© 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. 80608
    Prev
    Next
    INDEX
    Explanations

    ingredients and cooking instructions related to recipes

    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
    EIF
    -0.09
    رش
    -0.07
    inker
    -0.07
    æĬ¼
    -0.07
    uble
    -0.06
    cio
    -0.06
    ebb
    -0.06
    EEK
    -0.06
     Tray
    -0.06
    thon
    -0.06
    POSITIVE LOGITS
     separately
    0.08
    uka
    0.07
    adar
    0.07
    ouses
    0.07
     separate
    0.07
     seperate
    0.07
    xes
    0.07
     accordingly
    0.06
     Separate
    0.06
    iri
    0.06
    Activations Density 0.049%

    No Known Activations