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. 31-LLAMASCOPE-RES-131K
    6. 44213
    Prev
    Next
    INDEX
    Explanations

    special characters and programming-related keywords

    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
    ardin
    -0.07
    _TypeDef
    -0.06
    èĦ±
    -0.06
     ConfigurationManager
    -0.06
    assis
    -0.06
    ady
    -0.06
    istory
    -0.06
     Michelle
    -0.06
    CppClass
    -0.06
     Alert
    -0.06
    POSITIVE LOGITS
     Stream
    0.14
     Consumer
    0.13
     stream
    0.13
     Supplier
    0.13
    Consumer
    0.13
     Streams
    0.13
    Supplier
    0.13
     streams
    0.13
    Stream
    0.12
     supplier
    0.12
    Activations Density 0.008%

    No Known Activations