© 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. 89447
    Prev
    Next
    INDEX
    Explanations

    specific date ranges and the timing of events

    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
     Harden
    -0.08
    _BS
    -0.07
     olmam
    -0.07
    launcher
    -0.07
    ÛĮÙĨÚ©
    -0.07
    δÏģα
    -0.07
    ctxt
    -0.07
     ë²łìĬ¤íĬ¸
    -0.06
    liÄŁin
    -0.06
    лки
    -0.06
    POSITIVE LOGITS
     finale
    0.07
     final
    0.07
    etsk
    0.07
     cogn
    0.06
     cul
    0.06
     finishing
    0.06
     Kent
    0.06
     ending
    0.06
     Final
    0.06
     bids
    0.06
    Activations Density 0.005%

    No Known Activations