© 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. 15-LLAMASCOPE-RES-131K
    11. 86447
    Prev
    Next
    INDEX
    Explanations

    positive evaluations of products, particularly in the context of food and tech

    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
     itself
    -0.10
    ↵↵
    -0.07
    chnitt
    -0.07
    enders
    -0.07
    ëŁ
    -0.07
     Wikispecies
    -0.07
    çļĦä¸Ģ个
    -0.06
    æĺ¯ä¸ª
    -0.06
    apis
    -0.06
    Binder
    -0.06
    POSITIVE LOGITS
     themselves
    0.14
     коÑĤоÑĢÑĭе
    0.09
     thems
    0.08
    å®ĥ们
    0.07
     ÑıкÑĸ
    0.07
    “These
    0.07
     Ñģами
    0.07
     коÑĤоÑĢÑĭÑħ
    0.07
     originals
    0.07
    è¿ĻäºĽ
    0.07
    Activations Density 0.228%

    No Known Activations