© 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. 107369
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "the" in various contexts

    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
     Wikispecies
    -0.07
     onDataChange
    -0.06
    âĢ¦↵
    -0.06
    /stdc
    -0.06
    âĢ¦
    -0.06
    ..↵
    -0.06
    513
    -0.06
    Âłin
    -0.05
    croft
    -0.05
    CreateDate
    -0.05
    POSITIVE LOGITS
    #__
    0.11
    âĢ¦"↵↵
    0.09
    ï¼Ĭ
    0.09
    ắc
    0.09
    #ac
    0.09
    _________________↵↵
    0.09
    èm
    0.09
    quelle
    0.09
    ุà¸ļ
    0.08
    .Mask
    0.08
    Activations Density 0.199%

    No Known Activations