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. 44070
    Prev
    Next
    INDEX
    Explanations

    elements related to website templates or placeholders

    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
    onta
    -0.07
    sent
    -0.06
    885
    -0.06
    ANTA
    -0.06
    ente
    -0.06
     morale
    -0.06
    sole
    -0.06
     sola
    -0.06
    mith
    -0.06
    pling
    -0.05
    POSITIVE LOGITS
     maintained
    0.08
     introduction
    0.07
    /compiler
    0.07
    ulia
    0.07
    lyph
    0.06
    ÙĮ
    0.06
     biography
    0.06
     introducing
    0.06
    /repository
    0.06
    æĿ¡
    0.06
    Activations Density 0.001%

    No Known Activations