© 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 EvalsExportsAPI 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. 3491
    Prev
    Next
    INDEX
    Explanations

    metrics related to health outcomes in clinical trial data

    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
    ilan
    -0.08
     fat
    -0.08
    TYPO
    -0.07
    æijĺ
    -0.07
    zman
    -0.07
    enco
    -0.07
    alty
    -0.07
    SSI
    -0.07
    uhl
    -0.06
     dam
    -0.06
    POSITIVE LOGITS
     Difference
    0.07
     difference
    0.07
    Difference
    0.07
     superiority
    0.07
     placebo
    0.07
    Net
    0.07
     Mean
    0.06
    неÑĤ
    0.06
     Benefit
    0.06
    Touches
    0.06
    Activations Density 0.024%

    No Known Activations