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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 125537
    Prev
    Next
    INDEX
    Explanations

    expressions related to duration and longevity

    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
    uchs
    -0.07
    unj
    -0.07
    uez
    -0.07
     NI
    -0.07
     hâl
    -0.07
    ongyang
    -0.07
    egg
    -0.07
     sữa
    -0.07
    emey
    -0.06
     Slee
    -0.06
    POSITIVE LOGITS
    ingly
    0.10
     Longer
    0.10
     longer
    0.09
    -minute
    0.08
    .fm
    0.07
    long
    0.07
    arrera
    0.07
     until
    0.07
     forever
    0.06
     long
    0.06
    Activations Density 0.007%

    No Known Activations