© 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. 15-LLAMASCOPE-RES-131K
    11. 27366
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "the" in various contexts, indicating a focus on specifying particular subjects or entities in 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
    ãĥ«ãĤ¯
    -0.08
    muz
    -0.07
    swick
    -0.07
    ãĤĬãģ¨
    -0.07
    ìĦ±ìĿ´
    -0.07
    аÑĢÑĤ
    -0.07
    iez
    -0.07
    алог
    -0.07
    ĨĴ
    -0.07
    rians
    -0.07
    POSITIVE LOGITS
     alike
    0.09
     subsequently
    0.07
    /or
    0.07
    yon
    0.07
     others
    0.06
    /OR
    0.06
     Willis
    0.06
     its
    0.06
     equally
    0.06
    etime
    0.05
    Activations Density 0.050%

    No Known Activations