© 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. 70331
    Prev
    Next
    INDEX
    Explanations

    the word "the" as it relates to various contexts and frequencies within the text

    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
    .InnerException
    -0.08
    Ð¡Ðł
    -0.08
     ontvangst
    -0.07
    Ãłm
    -0.07
     çoÄŁ
    -0.07
    алÑİ
    -0.07
    ãĥ¬ãĤ¹
    -0.07
    ë°Ģ
    -0.07
     kapit
    -0.07
    .vm
    -0.07
    POSITIVE LOGITS
     world
    0.07
     globe
    0.06
     Dias
    0.06
    Hierarchy
    0.06
    odge
    0.06
    mma
    0.06
    CHAN
    0.06
    caffold
    0.06
     wherever
    0.06
    aved
    0.05
    Activations Density 0.013%

    No Known Activations