© 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. 70485
    Prev
    Next
    INDEX
    Explanations

    elements related to size, particularly in organizational or business contexts

    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
    insi
    -0.06
    ingen
    -0.06
    oust
    -0.06
    laus
    -0.06
    üme
    -0.06
     Milton
    -0.06
    âīł
    -0.06
    ammen
    -0.06
    Utility
    -0.06
    andin
    -0.06
    POSITIVE LOGITS
     small
    0.21
     smaller
    0.20
    small
    0.19
     Small
    0.19
    -small
    0.19
     SMALL
    0.19
    Small
    0.17
     smallest
    0.15
    .small
    0.15
     peque
    0.15
    Activations Density 0.157%

    No Known Activations