© 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. 127828
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to image sizes and formats

    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
    atcher
    -0.07
    501
    -0.07
    aeda
    -0.07
    ahy
    -0.06
    unge
    -0.06
    ään
    -0.06
     Spectrum
    -0.06
    endon
    -0.06
     Fur
    -0.06
    rray
    -0.06
    POSITIVE LOGITS
     sizes
    0.09
     size
    0.08
    fit
    0.08
    stu
    0.07
     scales
    0.07
    oir
    0.07
     dimensions
    0.07
     Scal
    0.07
     resolution
    0.07
    -sizing
    0.07
    Activations Density 0.003%

    No Known Activations