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. 43595
    Prev
    Next
    INDEX
    Explanations

    special mathematical symbols and notations

    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
    chner
    -0.08
     ......
    -0.07
     .....
    -0.06
    Å©
    -0.06
     Whilst
    -0.06
     ....↵↵
    -0.06
     ..↵
    -0.06
    áme
    -0.06
     ..
    -0.06
    hu
    -0.05
    POSITIVE LOGITS
     bike
    0.09
     cyclists
    0.09
     biking
    0.08
     riders
    0.08
     bikes
    0.07
     cyclist
    0.07
     wider
    0.07
     safety
    0.07
     DOT
    0.07
     sidewalk
    0.07
    Activations Density 0.004%

    No Known Activations