© 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. 129398
    Prev
    Next
    INDEX
    Explanations

    anatomical terms related to the body

    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
    iaux
    -0.07
    allon
    -0.07
    verty
    -0.07
     medial
    -0.07
    uml
    -0.06
    çİ°åľº
    -0.06
    zan
    -0.06
     flank
    -0.06
     ÙħÙĪب
    -0.06
     ÙħÙĪباÛĮÙĦ
    -0.06
    POSITIVE LOGITS
     region
    0.07
     muscles
    0.07
    pect
    0.06
    astr
    0.06
     foss
    0.06
     mus
    0.06
     proper
    0.06
    änner
    0.06
     Mus
    0.06
    infer
    0.06
    Activations Density 0.047%

    No Known Activations