© 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. 92968
    Prev
    Next
    INDEX
    Explanations

    references to legal processes and court rulings

    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
     prosecution
    -0.08
     prosecute
    -0.07
    ì·¨
    -0.07
    æİĮ
    -0.06
     Farr
    -0.06
     Scotch
    -0.06
    igits
    -0.06
     pours
    -0.06
     household
    -0.06
    ='<?
    -0.06
    POSITIVE LOGITS
    entina
    0.08
     Tunnel
    0.07
    _MO
    0.07
     tunnel
    0.07
    rights
    0.06
    bow
    0.06
    iani
    0.06
     habe
    0.06
     Tun
    0.06
     IDEA
    0.06
    Activations Density 0.057%

    No Known Activations