Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 29369
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to kidney infections and their complications

    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
    ARGIN
    -0.07
     informational
    -0.07
    ieu
    -0.07
    .getAs
    -0.07
    .onView
    -0.07
    ocht
    -0.07
    piler
    -0.07
    itou
    -0.07
    .Argument
    -0.07
    št
    -0.06
    POSITIVE LOGITS
     most
    0.06
    nos
    0.06
    quiz
    0.06
     nos
    0.06
     of
    0.06
     rarity
    0.06
    ocker
    0.06
     usually
    0.06
     paraph
    0.06
     tri
    0.06
    Activations Density 0.086%

    No Known Activations