© 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. 73369
    Prev
    Next
    INDEX
    Explanations

    concepts related to anniversaries and significant time markers

    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
    ç¼
    -0.06
    æĻ¨
    -0.06
    cou
    -0.06
    uess
    -0.06
    Ø´ÙĪر
    -0.06
    conduct
    -0.06
     Bol
    -0.06
    .twig
    -0.06
    oker
    -0.06
     extr
    -0.05
    POSITIVE LOGITS
     anniversary
    0.15
     Anniversary
    0.13
     birthday
    0.11
    åij¨å¹´
    0.10
    birthday
    0.10
    ä¸īå¹´
    0.08
    iversary
    0.08
     Birthday
    0.08
    irthday
    0.08
    uze
    0.07
    Activations Density 0.043%

    No Known Activations