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. 11527
    Prev
    Next
    INDEX
    Explanations

    specific character sequences or symbols, possibly related to programming or markup languages

    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
    Âł
    -0.07
    ...↵
    -0.07
     DERP
    -0.06
    Âł↵
    -0.06
     Pew
    -0.06
     STEM
    -0.06
     Netflix
    -0.06
     Haiti
    -0.06
     Lyft
    -0.06
    Âł↵↵
    -0.06
    POSITIVE LOGITS
     Lawyers
    0.12
     Lawyer
    0.11
     lawyer
    0.10
     lawyers
    0.10
     Developer
    0.10
     Developers
    0.10
    Developer
    0.09
     developer
    0.09
     MV
    0.09
     lawy
    0.09
    Activations Density 0.001%

    No Known Activations