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. 44297
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols, often used in mathematical and scientific contexts

    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
     Austin
    -0.07
     Hawaii
    -0.06
     Nashville
    -0.06
     SX
    -0.06
     Prairie
    -0.06
     Prescott
    -0.06
     Hawai
    -0.06
     Smithsonian
    -0.06
     Texans
    -0.06
     Portland
    -0.06
    POSITIVE LOGITS
     Alban
    0.16
     MOS
    0.15
     Mos
    0.14
     Albania
    0.14
     Kosovo
    0.13
    Mos
    0.13
     mos
    0.12
     Bos
    0.12
     IB
    0.11
     Bosnia
    0.10
    Activations Density 0.004%

    No Known Activations