© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 84606
    Prev
    Next
    INDEX
    Explanations

    references to musical performance and success

    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
    ander
    -0.06
    -archive
    -0.06
    egas
    -0.06
    orry
    -0.06
    eb
    -0.06
    _HANDLE
    -0.06
     furn
    -0.06
     actors
    -0.06
    _dash
    -0.06
     Mime
    -0.06
    POSITIVE LOGITS
    Indented
    0.07
    _FM
    0.07
     FM
    0.07
     Sokol
    0.07
     underground
    0.06
     steadily
    0.06
    omentum
    0.06
    TestFixture
    0.06
    .fm
    0.06
     slowly
    0.06
    Activations Density 0.034%

    No Known Activations