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. 5563
    Prev
    Next
    INDEX
    Explanations

    references to academic classes and their statistics

    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
     Darling
    -0.06
    Ī
    -0.06
    ãĤ«ãĥĨãĤ´ãĥª
    -0.06
     toward
    -0.06
     æĹ
    -0.06
    341
    -0.06
    aso
    -0.06
    iti
    -0.06
     خاطر
    -0.06
    avar
    -0.05
    POSITIVE LOGITS
     Class
    0.09
    Class
    0.07
    TestClass
    0.07
     CLASS
    0.07
    -minus
    0.07
    class
    0.07
    -Class
    0.07
    CLASS
    0.07
    (Class
    0.07
    airs
    0.06
    Activations Density 0.003%

    No Known Activations