© 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. 119304
    Prev
    Next
    INDEX
    Explanations

    references to the name "Kurt."

    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
    ovali
    -0.08
    fluid
    -0.07
    riz
    -0.07
    erty
    -0.07
    BJECT
    -0.07
    hood
    -0.07
    Truthy
    -0.07
    yg
    -0.07
    ras
    -0.07
    677
    -0.07
    POSITIVE LOGITS
    tle
    0.07
    anity
    0.06
    &page
    0.06
    aceous
    0.06
    ÑĮи
    0.06
    yle
    0.06
    ters
    0.06
    ayne
    0.06
    ا
    0.05
     Guill
    0.05
    Activations Density 0.006%

    No Known Activations