© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 94424
    Prev
    Next
    INDEX
    Explanations

    elements related to colors and visual patterns

    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
    adh
    -0.07
    airs
    -0.07
    ystate
    -0.07
    ivre
    -0.07
    ris
    -0.06
     ventil
    -0.06
    ãĥªãĤ¢
    -0.06
    iveau
    -0.06
    peer
    -0.06
    oux
    -0.06
    POSITIVE LOGITS
     chrom
    0.10
     hue
    0.09
     hues
    0.09
     color
    0.08
     Chrom
    0.08
    chrom
    0.08
     colors
    0.08
     Pant
    0.08
     Wheel
    0.08
     Color
    0.08
    Activations Density 0.046%

    No Known Activations