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. 5720
    Prev
    Next
    INDEX
    Explanations

    section headers and formatting elements

    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
    окÑĢема
    -0.07
    #ac
    -0.07
    åı¦ä¸Ģ
    -0.07
    #End
    -0.07
    oque
    -0.07
    ÏĦÏģα
    -0.06
    داÙĨÙĦÙĪØ¯
    -0.06
    دÛĮگر
    -0.06
    icari
    -0.06
    надлеж
    -0.06
    POSITIVE LOGITS
     ###
    0.08
    TODO
    0.08
     ####
    0.08
     TBD
    0.08
    ####
    0.07
     There
    0.07
    ###
    0.07
     This
    0.07
    _TODO
    0.07
     Because
    0.07
    Activations Density 0.011%

    No Known Activations