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. 44088
    Prev
    Next
    INDEX
    Explanations

    references to ceremonial or ritualistic practices

    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
     Newman
    -0.07
    Sugar
    -0.06
     socialism
    -0.06
     Zucker
    -0.06
     Manchester
    -0.06
    indi
    -0.06
     Lancaster
    -0.06
     Sears
    -0.06
    Bang
    -0.06
     wallpaper
    -0.06
    POSITIVE LOGITS
     Apollo
    0.16
     oracle
    0.15
     Oracle
    0.14
     Py
    0.14
    Apollo
    0.13
     Del
    0.13
    Oracle
    0.12
    oracle
    0.12
     Python
    0.11
     proph
    0.10
    Activations Density 0.009%

    No Known Activations