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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 77697
    Prev
    Next
    INDEX
    Explanations

    references to formal events and awards ceremonies

    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
     clock
    -0.06
    mour
    -0.06
    -clock
    -0.06
    oun
    -0.05
    ãĤ¤ãĤ¹
    -0.05
    ffiti
    -0.05
    okus
    -0.05
     Mour
    -0.05
     uniform
    -0.05
     Alonso
    -0.05
    POSITIVE LOGITS
     awards
    0.11
     Awards
    0.10
     ceremony
    0.09
    CommandEvent
    0.08
     ла
    0.08
     award
    0.07
    held
    0.07
     ìĪĺìĥģ
    0.07
     dinner
    0.07
    å¼ı
    0.07
    Activations Density 0.026%

    No Known Activations