© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 74012
    Prev
    Next
    INDEX
    Explanations

    references to artificial sweeteners and their health implications

    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
    wer
    -0.07
    ĸī
    -0.06
    elize
    -0.06
    ocê
    -0.06
     Santana
    -0.06
    ikon
    -0.06
    atham
    -0.06
     sát
    -0.06
    phans
    -0.06
     Minist
    -0.06
    POSITIVE LOGITS
     study
    0.09
     researchers
    0.09
     scientists
    0.08
     Researchers
    0.08
     research
    0.08
     researcher
    0.08
     findings
    0.07
     scientist
    0.07
    ç§ijåѦ
    0.07
    AGER
    0.07
    Activations Density 0.028%

    No Known Activations