© 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. 75965
    Prev
    Next
    INDEX
    Explanations

    descriptors related to duration or longevity in specific 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
    359
    -0.07
    947
    -0.06
    mie
    -0.06
    indle
    -0.06
    les
    -0.06
    akan
    -0.06
    dig
    -0.06
    ìłĢ
    -0.06
    sein
    -0.06
    utto
    -0.06
    POSITIVE LOGITS
     longest
    0.10
    éĤ¦
    0.09
     Longer
    0.08
    ablish
    0.08
    -lasting
    0.08
     dÃłi
    0.07
    .LENGTH
    0.07
     duration
    0.07
    duration
    0.07
     longer
    0.07
    Activations Density 0.003%

    No Known Activations