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. 43639
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols within 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
     Vanderbilt
    -0.07
     Titanic
    -0.07
    avern
    -0.06
     Nikola
    -0.06
    entar
    -0.06
     Holocaust
    -0.06
    obra
    -0.06
    agner
    -0.06
     ---↵
    -0.06
     ---
    -0.06
    POSITIVE LOGITS
     riders
    0.13
     rider
    0.13
     riding
    0.13
     Riders
    0.12
     filmer
    0.12
     bike
    0.11
     Trials
    0.11
     trials
    0.11
     BM
    0.11
     biking
    0.11
    Activations Density 0.003%

    No Known Activations