© 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. 59116
    Prev
    Next
    INDEX
    Explanations

    references to dye-related processes and products

    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
    abi
    -0.07
     dust
    -0.07
    dust
    -0.06
     polished
    -0.06
     frozen
    -0.06
     carb
    -0.06
     dynam
    -0.05
     Roof
    -0.05
     roof
    -0.05
    æ¼Ķ
    -0.05
    POSITIVE LOGITS
     pigment
    0.08
    æŁĵ
    0.08
     dye
    0.08
    color
    0.07
    èī²çļĦ
    0.07
     color
    0.07
    λÏī
    0.07
    /color
    0.07
    _tF
    0.07
    鬼
    0.07
    Activations Density 0.003%

    No Known Activations