© 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. 93921
    Prev
    Next
    INDEX
    Explanations

    references to comic books and notable characters within them

    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
    æĪı
    -0.07
    «ĺ
    -0.07
    TINGS
    -0.07
    ãĥ¼ãĥĢ
    -0.07
    iley
    -0.07
    nnen
    -0.07
    Carthy
    -0.06
    ë¶Ī
    -0.06
    ogue
    -0.06
    öyle
    -0.06
    POSITIVE LOGITS
     Ever
    0.07
     brands
    0.07
     websites
    0.06
     EVER
    0.06
     Christmas
    0.06
    Ever
    0.06
    ä¹ĭä¸Ģ
    0.06
     companies
    0.06
     names
    0.06
    assist
    0.06
    Activations Density 0.028%

    No Known Activations