© 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. 9-LLAMASCOPE-RES-131K
    11. 95426
    Prev
    Next
    INDEX
    Explanations

    medical terms specifically related to fractures and anatomy

    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
    ieties
    -0.07
    oppel
    -0.07
    Disappear
    -0.07
    è°±
    -0.07
    ollen
    -0.07
    anners
    -0.07
    nesc
    -0.07
    ãĥ³ãĥĶ
    -0.07
    utex
    -0.07
    ìł¤
    -0.07
    POSITIVE LOGITS
     Hoy
    0.06
    rak
    0.06
     tarn
    0.05
    atham
    0.05
    orial
    0.05
     productivity
    0.05
    hm
    0.05
    ils
    0.05
    ack
    0.05
    yw
    0.05
    Activations Density 0.001%

    No Known Activations