© 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 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. 119229
    Prev
    Next
    INDEX
    Explanations

    the word "meanwhile" as a narrative transitional phrase

    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
    nt
    -0.07
     tháºŃm
    -0.07
     indeed
    -0.07
     hatta
    -0.07
    de
    -0.06
    ud
    -0.06
    ali
    -0.06
    ula
    -0.06
    /or
    -0.06
    sock
    -0.06
    POSITIVE LOGITS
    forth
    0.11
    że
    0.09
    abcdefghijklmnop
    0.08
    Ùĭ
    0.07
    ständ
    0.07
     ç«ĭ
    0.07
    quam
    0.07
    ë¡ľëĬĶ
    0.07
    ìĹIJëıĦ
    0.07
    icari
    0.07
    Activations Density 0.006%

    No Known Activations