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. 43403
    Prev
    Next
    INDEX
    Explanations

    instances of specific symbols or characters, possibly representing functions or parameters in technical content

    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
     Organizations
    -0.08
     organized
    -0.08
     organizing
    -0.08
     organize
    -0.08
     organization
    -0.08
     organizational
    -0.08
     organizations
    -0.07
     civilization
    -0.07
     hospitalized
    -0.07
     polarization
    -0.07
    POSITIVE LOGITS
     exporting
    0.13
     export
    0.13
    Export
    0.13
     exports
    0.13
     Export
    0.13
     exported
    0.12
     exporters
    0.12
     EXPORT
    0.12
    EXPORT
    0.12
     exporter
    0.11
    Activations Density 0.006%

    No Known Activations