© 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. 2829
    Prev
    Next
    INDEX
    Explanations

    references to seed saving and related gardening practices

    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
    森
    -0.07
     beled
    -0.07
    æ³ī
    -0.07
    deen
    -0.07
    íĹĮ
    -0.06
    æ´ŀ
    -0.06
    CDATA
    -0.06
    flush
    -0.06
    éré
    -0.06
    νÏĦ
    -0.06
    POSITIVE LOGITS
     seed
    0.10
     seeds
    0.10
     Seeds
    0.08
    .seed
    0.08
     Seed
    0.08
     genetic
    0.08
     reproduce
    0.07
    æĴŃ
    0.07
     sperma
    0.06
     reprodu
    0.06
    Activations Density 0.026%

    No Known Activations