© 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. 22-LLAMASCOPE-RES-131K
    11. 3650
    Prev
    Next
    INDEX
    Explanations

    aspects related to food and culinary experiences

    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
     ÏĮμÏīÏĤ
    -0.06
    ut
    -0.06
    hong
    -0.06
    æľīä¸Ģ
    -0.06
    onda
    -0.06
    usz
    -0.06
    æ¦
    -0.06
    Printf
    -0.05
    ê°ľìĿĺ
    -0.05
    arn
    -0.05
    POSITIVE LOGITS
     chez
    0.12
     tại
    0.10
     during
    0.09
    æĶ¾åľ¨
    0.09
     æĸ¼
    0.09
     bei
    0.09
     trên
    0.08
     within
    0.08
     at
    0.08
     lors
    0.08
    Activations Density 0.424%

    No Known Activations