© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 106298
    Prev
    Next
    INDEX
    Explanations

    phrases related to longevity and sustainability

    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
    ild
    -0.06
    ich
    -0.06
    vé
    -0.06
    ÐĦ
    -0.06
    ync
    -0.05
    ony
    -0.05
     jew
    -0.05
     earlier
    -0.05
     Perf
    -0.05
    á»ĵ
    -0.05
    POSITIVE LOGITS
     until
    0.10
     lifelong
    0.10
     longevity
    0.10
     future
    0.10
     lifetime
    0.09
     Until
    0.09
    until
    0.09
    future
    0.09
    æľªæĿ¥
    0.09
     long
    0.09
    Activations Density 0.031%

    No Known Activations