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. 43822
    Prev
    Next
    INDEX
    Explanations

    patterns of code structure and numeric values in technical or programming contexts

    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
     books
    -0.10
     teams
    -0.09
     tables
    -0.09
    (files
    -0.09
     streets
    -0.09
     files
    -0.09
     pages
    -0.09
     stores
    -0.08
     ages
    -0.08
     blogs
    -0.08
    POSITIVE LOGITS
    111
    0.21
    311
    0.14
    511
    0.14
    411
    0.13
    711
    0.13
    211
    0.13
    Û±Û±
    0.12
    811
    0.11
    611
    0.11
    911
    0.10
    Activations Density 0.012%

    No Known Activations