© 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. 15-LLAMASCOPE-RES-131K
    11. 62313
    Prev
    Next
    INDEX
    Explanations

    expressions related to data processing and mathematical calculations

    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
    ilm
    -0.08
     afterwards
    -0.07
    .dst
    -0.07
     afterward
    -0.07
    902
    -0.07
    MaxY
    -0.07
    bol
    -0.07
    Later
    -0.07
     pant
    -0.06
    uzzi
    -0.06
    POSITIVE LOGITS
     earlier
    0.11
     Earlier
    0.09
     earliest
    0.08
    Earlier
    0.07
    ear
    0.07
     pre
    0.07
    æĹ©
    0.07
     Pre
    0.07
     Ear
    0.07
     preceding
    0.07
    Activations Density 0.054%

    No Known Activations