© 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. 130958
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to oligosaccharides

    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
    lÃŃÄį
    -0.07
    ázi
    -0.07
    lite
    -0.07
    ìĽħ
    -0.07
    oglobin
    -0.07
    opers
    -0.07
     alive
    -0.07
    oglob
    -0.07
    elan
    -0.07
    arl
    -0.06
    POSITIVE LOGITS
    ivia
    0.08
    mos
    0.07
    uder
    0.07
    ensch
    0.07
     Ol
    0.07
    bek
    0.07
    en
    0.06
    arity
    0.06
    con
    0.06
     fashioned
    0.06
    Activations Density 0.014%

    No Known Activations