© 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. 41513
    Prev
    Next
    INDEX
    Explanations

    connections between artistic expressions and broader themes or concepts

    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
     issued
    -0.06
    /uploads
    -0.06
    ogle
    -0.06
     someone
    -0.05
     prospect
    -0.05
    pler
    -0.05
    ueva
    -0.05
    æijĺ
    -0.05
     kill
    -0.05
    433
    -0.05
    POSITIVE LOGITS
     presente
    0.09
     reflected
    0.08
     present
    0.07
    onen
    0.07
     apparent
    0.07
     evident
    0.07
    å«Į
    0.07
    QRST
    0.07
    ÙĬÙĩ
    0.07
     influence
    0.07
    Activations Density 0.034%

    No Known Activations