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. 44027
    Prev
    Next
    INDEX
    Explanations

    references to event handling and configuration management

    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
    _endian
    -0.06
    upported
    -0.06
     Mode
    -0.06
    /testify
    -0.06
    /tinyos
    -0.06
    Charsets
    -0.05
     platforms
    -0.05
     Rated
    -0.05
    appen
    -0.05
    oftware
    -0.05
    POSITIVE LOGITS
     contents
    0.13
     value
    0.12
     object
    0.12
    's
    0.12
     itself
    0.11
     information
    0.10
     variable
    0.10
    Contents
    0.10
     being
    0.09
    contents
    0.09
    Activations Density 0.115%

    No Known Activations