© 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. 126524
    Prev
    Next
    INDEX
    Explanations

    variations of the word "gleam" and its related forms

    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
    ettes
    -0.06
    plane
    -0.06
    gies
    -0.06
    nze
    -0.06
    erah
    -0.06
    t
    -0.06
    heimer
    -0.06
    ates
    -0.06
    ÙĪÛĮد
    -0.05
    اپ
    -0.05
    POSITIVE LOGITS
    .Glide
    0.10
    eful
    0.09
     gl
    0.08
    .gl
    0.08
    ible
    0.07
    ular
    0.07
     Gl
    0.07
    enario
    0.07
    oux
    0.07
    ewis
    0.07
    Activations Density 0.002%

    No Known Activations