© 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. 15931
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to awards and recognitions in various fields

    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
    licos
    -0.09
    icum
    -0.08
    vern
    -0.08
    allen
    -0.08
    .Automation
    -0.07
    داÙĨÙĦÙĪد
    -0.07
    ATEST
    -0.07
    /problems
    -0.07
    ÌĨ
    -0.07
    quoise
    -0.07
    POSITIVE LOGITS
     Ever
    0.08
    ä¹ĭä¸Ģ
    0.07
     category
    0.07
     overall
    0.07
     ever
    0.07
    -ever
    0.06
     categories
    0.06
    categorie
    0.06
    category
    0.06
    Ever
    0.06
    Activations Density 0.016%

    No Known Activations