© 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. 96177
    Prev
    Next
    INDEX
    Explanations

    references to food alternatives and non-food items for celebrations

    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
    antes
    -0.07
     eb
    -0.07
    rvine
    -0.06
    aldi
    -0.06
    aho
    -0.06
    ìĿ´íģ¬
    -0.06
    pcf
    -0.06
    iales
    -0.06
    enta
    -0.06
     evangel
    -0.06
    POSITIVE LOGITS
    onium
    0.07
     spa
    0.06
    oucher
    0.06
    usi
    0.06
    882
    0.06
     something
    0.06
     increments
    0.06
    -utils
    0.06
     Perf
    0.06
    .fromLTRB
    0.06
    Activations Density 0.006%

    No Known Activations