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

    Neuronpedia

    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. 15774
    Prev
    Next
    INDEX
    Explanations

    instructional language concerning medical principles and procedures

    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
    kili
    -0.08
     COPYING
    -0.07
    ote
    -0.07
    UNUSED
    -0.07
    rá
    -0.07
    ray
    -0.07
    Æ°á»Ľ
    -0.07
     FAQ
    -0.07
    eydi
    -0.07
    atism
    -0.06
    POSITIVE LOGITS
     ways
    0.07
     understand
    0.06
    uppy
    0.06
    izia
    0.06
     difference
    0.06
     understanding
    0.06
    ä¸Ģä¸ĭ
    0.06
     concept
    0.06
    º«
    0.06
     role
    0.06
    Activations Density 0.019%

    No Known Activations