© 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. 69715
    Prev
    Next
    INDEX
    Explanations

    references to workplace injuries and their consequences

    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
    ÃŃna
    -0.07
    enko
    -0.06
     powder
    -0.06
    isten
    -0.06
    isease
    -0.06
     jaws
    -0.06
     hadn
    -0.06
     mouths
    -0.06
    olver
    -0.06
    ara
    -0.05
    POSITIVE LOGITS
    wort
    0.07
    боÑĤ
    0.07
    illions
    0.07
    reck
    0.07
    chwitz
    0.07
    bsub
    0.07
    çĬ¶
    0.07
    λμ
    0.06
    веÑī
    0.06
    rette
    0.06
    Activations Density 0.006%

    No Known Activations