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. 22-LLAMASCOPE-RES-131K
    6. 5451
    Prev
    Next
    INDEX
    Explanations

    references to musical content or lyrics

    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
    estr
    -0.07
    cell
    -0.06
     Foley
    -0.06
     Fulton
    -0.06
     Tou
    -0.06
    thur
    -0.05
    å¼ı
    -0.05
    ella
    -0.05
    .init
    -0.05
    istingu
    -0.05
    POSITIVE LOGITS
    Ly
    0.08
     LY
    0.08
     lyric
    0.07
     Ly
    0.07
    -translate
    0.07
    غÙĨ
    0.07
    .metro
    0.07
    /licenses
    0.07
    otte
    0.07
     lyrics
    0.06
    Activations Density 0.001%

    No Known Activations