© 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. 78331
    Prev
    Next
    INDEX
    Explanations

    products or items related to gemstones and collectibles

    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
     Leather
    -0.07
    erson
    -0.07
    ilet
    -0.06
     leather
    -0.06
    ement
    -0.06
    PÅĻi
    -0.06
    erton
    -0.06
    414
    -0.06
     ढ
    -0.06
    quet
    -0.06
    POSITIVE LOGITS
     Crystal
    0.10
     crystal
    0.10
    Crystal
    0.09
    شب
    0.08
     numberWith
    0.08
     cryst
    0.08
    ÏĢή
    0.08
    zier
    0.07
    æĺŁ
    0.07
    PEND
    0.07
    Activations Density 0.001%

    No Known Activations