© 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 EvalsExportsinterp-engineNEWAPI 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. 14822
    Prev
    Next
    INDEX
    Explanations

    references to the passage of time, particularly in years

    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
     Innoc
    -0.06
    ola
    -0.05
    byname
    -0.05
    è´
    -0.05
     kans
    -0.05
     gradual
    -0.05
    765
    -0.05
    istributed
    -0.05
     overall
    -0.05
    avis
    -0.05
    POSITIVE LOGITS
    IVERY
    0.08
    auer
    0.07
    apest
    0.07
    achsen
    0.07
    icha
    0.07
     intervening
    0.07
    dma
    0.07
    AUD
    0.07
    ityEngine
    0.07
    iefs
    0.07
    Activations Density 0.015%

    No Known Activations