© 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. 41583
    Prev
    Next
    INDEX
    Explanations

    artistic terminology and concepts related to art

    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
    Dual
    -0.06
    ailed
    -0.06
     ...↵↵
    -0.06
     Lookup
    -0.05
     bình
    -0.05
    анÑģи
    -0.05
     endeavors
    -0.05
     Checkout
    -0.05
    èĥ½å¤Ł
    -0.05
    nes
    -0.05
    POSITIVE LOGITS
     https
    0.08
    =https
    0.07
     schle
    0.07
    mium
    0.07
     tho
    0.06
    ennie
    0.06
    ÐŀÐĿ
    0.06
    :maj
    0.06
    PIX
    0.06
    gaard
    0.06
    Activations Density 0.000%

    No Known Activations