© 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. 63031
    Prev
    Next
    INDEX
    Explanations

    references to dairy products and their properties

    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
     fung
    -0.07
    éŁĵ
    -0.07
    fty
    -0.06
    ebi
    -0.06
     minlength
    -0.06
    berman
    -0.06
    imson
    -0.06
     damp
    -0.06
    igmoid
    -0.06
    azor
    -0.06
    POSITIVE LOGITS
     milk
    0.17
     dairy
    0.15
     Milk
    0.14
     lact
    0.13
     Dairy
    0.13
     mil
    0.13
     sữa
    0.11
     Milky
    0.11
    奶
    0.11
    ä¹³
    0.11
    Activations Density 0.017%

    No Known Activations