© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 107125
    Prev
    Next
    INDEX
    Explanations

    descriptions of colors and visual imagery

    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
     Orange
    -0.07
     orange
    -0.07
    orex
    -0.07
     redd
    -0.07
     Red
    -0.06
     red
    -0.06
    红
    -0.06
    èľľ
    -0.06
    ymoon
    -0.06
    èħIJ
    -0.06
    POSITIVE LOGITS
     blue
    0.17
    blue
    0.16
    -blue
    0.16
     Blue
    0.16
    Blue
    0.16
     BLUE
    0.15
    BLUE
    0.15
    .blue
    0.13
    _blue
    0.13
    _Blue
    0.12
    Activations Density 0.039%

    No Known Activations