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. 44389
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols that may represent mathematical or abstract concepts

    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
    /DTD
    -0.06
    ibus
    -0.06
     Township
    -0.06
    baum
    -0.06
     township
    -0.06
    umen
    -0.06
    odus
    -0.05
    éİ®
    -0.05
     amen
    -0.05
    POS
    -0.05
    POSITIVE LOGITS
     Pharma
    0.12
     Vaccine
    0.11
     vaccine
    0.11
     vaccines
    0.10
     vacc
    0.10
     Vacc
    0.10
     mRNA
    0.10
     pharmaceutical
    0.10
     Pfizer
    0.10
     vaccination
    0.09
    Activations Density 0.002%

    No Known Activations