© 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. 92588
    Prev
    Next
    INDEX
    Explanations

    references to music and creativity, particularly in relation to original works and 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
    ermann
    -0.06
    elper
    -0.06
    compact
    -0.06
    >window
    -0.06
    ordin
    -0.06
     WX
    -0.06
    USES
    -0.06
    selling
    -0.05
    olis
    -0.05
    Uni
    -0.05
    POSITIVE LOGITS
     manufacture
    0.11
     production
    0.11
    åĪ¶ä½ľ
    0.11
     custom
    0.10
     manufact
    0.10
     Production
    0.10
    -production
    0.10
     manufacturing
    0.10
     homemade
    0.10
     ìłľìŀij
    0.10
    Activations Density 0.107%

    No Known Activations