© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 60817
    Prev
    Next
    INDEX
    Explanations

    elements related to entertainment and performance traditions

    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
    rack
    -0.07
    eyh
    -0.07
    pond
    -0.07
    .echo
    -0.07
    -urlencoded
    -0.07
    essa
    -0.07
    ulin
    -0.07
    olis
    -0.07
     å½±
    -0.06
    hound
    -0.06
    POSITIVE LOGITS
     tradition
    0.10
     traditional
    0.08
     traditions
    0.08
     Tradition
    0.07
     Traditional
    0.07
    traditional
    0.07
     traditionally
    0.07
     annually
    0.06
    BOOT
    0.06
    Traditional
    0.06
    Activations Density 0.001%

    No Known Activations