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. 43547
    Prev
    Next
    INDEX
    Explanations

    symbols and characters from various non-Latin writing systems or specialized 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
     precinct
    -0.06
     Apparel
    -0.06
    érica
    -0.06
     Latino
    -0.05
    athon
    -0.05
     Latinos
    -0.05
    jez
    -0.05
     æħ
    -0.05
     Bags
    -0.05
     rub
    -0.05
    POSITIVE LOGITS
     Mushroom
    0.12
     Tolkien
    0.11
     fairy
    0.10
     mushroom
    0.10
     Michigan
    0.10
     mushrooms
    0.10
     Fairy
    0.10
     gnome
    0.09
     Dumbledore
    0.09
     Hob
    0.09
    Activations Density 0.003%

    No Known Activations