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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 117689
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate music and artistic performance

    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
    ÄĽnÃŃ
    -0.08
    precated
    -0.07
    ë»
    -0.07
     czy
    -0.07
    bane
    -0.06
    aÄŁ
    -0.06
    ë¦ī
    -0.06
    amics
    -0.06
    fé
    -0.06
     åĮ
    -0.06
    POSITIVE LOGITS
     earning
    0.08
     eventually
    0.07
    çīĪ
    0.07
     eventual
    0.06
     bil
    0.06
     nomin
    0.06
     becoming
    0.06
    part
    0.06
     most
    0.06
     Eventually
    0.06
    Activations Density 0.031%

    No Known Activations