© 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. 116870
    Prev
    Next
    INDEX
    Explanations

    objects, locations, and events associated with various activities and experiences

    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
    GD
    -0.07
    ones
    -0.07
     ¿
    -0.06
     sometimes
    -0.06
     often
    -0.06
     goo
    -0.05
     Lam
    -0.05
    816
    -0.05
     shaken
    -0.05
     ¡
    -0.05
    POSITIVE LOGITS
     itself
    0.13
     themselves
    0.09
     Himself
    0.09
     Fowler
    0.09
     herself
    0.08
    -ÑĤо
    0.08
    uiltin
    0.08
    fusion
    0.07
     há»į
    0.07
    enza
    0.07
    Activations Density 0.064%

    No Known Activations