© 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. 30565
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and structure elements in programming syntax

    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
    uffs
    -0.07
    auer
    -0.06
    vy
    -0.06
     toc
    -0.06
    ç®
    -0.06
    assy
    -0.06
    ugs
    -0.06
    distinct
    -0.06
    οÏį
    -0.06
     iw
    -0.06
    POSITIVE LOGITS
     Lair
    0.07
     import
    0.07
     class
    0.06
     imports
    0.06
    imports
    0.06
    alker
    0.06
    enu
    0.06
    éĵ¶
    0.06
    .AnchorStyles
    0.06
     classe
    0.06
    Activations Density 0.001%

    No Known Activations