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. 44405
    Prev
    Next
    INDEX
    Explanations

    characters or symbols that indicate specific encoding or formatting in 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
     Euler
    -0.07
     Twitter
    -0.07
     Marseille
    -0.06
    Egypt
    -0.06
     TTC
    -0.06
     Egypt
    -0.06
     WhatsApp
    -0.06
    ário
    -0.06
     Egyptian
    -0.06
     Dün
    -0.06
    POSITIVE LOGITS
     Alaska
    0.18
     Russ
    0.18
     salmon
    0.16
     Salmon
    0.15
    Russ
    0.14
     russ
    0.13
     Russell
    0.12
     Seattle
    0.11
     Rus
    0.11
     Siber
    0.11
    Activations Density 0.003%

    No Known Activations