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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5721
    Prev
    Next
    INDEX
    Explanations

    specific times and dates for events

    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
    ureau
    -0.07
     Intersection
    -0.06
    iren
    -0.06
     Honour
    -0.06
    راÙĨÛĮ
    -0.06
    ¢åįķ
    -0.06
    alls
    -0.06
    .openapi
    -0.06
    çĭ¬
    -0.06
    ammers
    -0.06
    POSITIVE LOGITS
    astle
    0.07
    ::*
    0.07
     boo
    0.07
    ÑĢÑĸÑĪ
    0.07
     Boo
    0.07
    /Runtime
    0.07
    EventHandler
    0.06
    uzzi
    0.06
    aviest
    0.06
    nette
    0.06
    Activations Density 0.005%

    No Known Activations