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. 5778
    Prev
    Next
    INDEX
    Explanations

    references to theatrical or performance-related 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
    gio
    -0.08
     Madden
    -0.08
    ylland
    -0.07
     terminal
    -0.07
    terminal
    -0.07
    esso
    -0.06
    yx
    -0.06
    鹿
    -0.06
    zione
    -0.06
    ç·Ĵ
    -0.06
    POSITIVE LOGITS
     MST
    0.10
     Franken
    0.07
     hosts
    0.07
    BorderStyle
    0.07
    /tos
    0.07
    íĴĪ
    0.07
    ondo
    0.07
    buster
    0.07
    pedia
    0.06
    _bot
    0.06
    Activations Density 0.005%

    No Known Activations