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. 43759
    Prev
    Next
    INDEX
    Explanations

    references to musical artists and their contributions to a film's soundtrack

    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
    COPE
    -0.09
    .dds
    -0.07
     Kurdistan
    -0.07
     CCT
    -0.07
     Všech
    -0.07
    CppClass
    -0.07
     Welsh
    -0.07
     Karnataka
    -0.07
    kart
    -0.07
     Baxter
    -0.07
    POSITIVE LOGITS
     Hamilton
    0.23
     Lin
    0.18
    Hamilton
    0.18
     Miranda
    0.17
    Lin
    0.15
     Alexander
    0.14
     Ham
    0.14
     ham
    0.12
     LIN
    0.12
     Lincoln
    0.12
    Activations Density 0.009%

    No Known Activations