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. 43755
    Prev
    Next
    INDEX
    Explanations

    unique and diverse characters or symbols in the text

    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
     Australians
    -0.07
     Australian
    -0.07
     Australia
    -0.07
     Adelaide
    -0.07
    Australian
    -0.06
    Australia
    -0.06
     Austral
    -0.06
    ustral
    -0.06
     international
    -0.06
    iad
    -0.06
    POSITIVE LOGITS
     Junior
    0.11
     junior
    0.11
     Jun
    0.10
    Junior
    0.10
     Touch
    0.10
     juni
    0.10
    jun
    0.09
    -Jun
    0.09
     Registr
    0.09
     female
    0.09
    Activations Density 0.004%

    No Known Activations