© 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. 42452
    Prev
    Next
    INDEX
    Explanations

    terms related to the efficacy and properties of antibacterial and anti-inflammatory substances

    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
    utin
    -0.08
    celik
    -0.07
    üstü
    -0.07
    /site
    -0.07
    _MT
    -0.07
     sắc
    -0.07
    sik
    -0.06
    çĴĥ
    -0.06
    cona
    -0.06
    wik
    -0.06
    POSITIVE LOGITS
     against
    0.07
    694
    0.06
     potential
    0.06
    宿
    0.06
    aze
    0.06
     lab
    0.06
    ảng
    0.06
    ams
    0.06
    OwnProperty
    0.06
     Against
    0.06
    Activations Density 0.030%

    No Known Activations