© 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. 27387
    Prev
    Next
    INDEX
    Explanations

    coding-related terminology, specifically in the context of variable declaration and configuration comments

    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
    aż
    -0.07
    .VisualBasic
    -0.07
    loi
    -0.06
     Luxembourg
    -0.06
    ilk
    -0.06
    okus
    -0.06
    itta
    -0.06
     FirebaseAuth
    -0.06
    ænd
    -0.06
    rous
    -0.06
    POSITIVE LOGITS
    PRETTY
    0.07
    åıİ
    0.06
    öh
    0.06
    GLOSS
    0.06
    SearchTree
    0.06
    ometr
    0.06
    Edition
    0.06
     pent
    0.06
     online
    0.06
     Kad
    0.06
    Activations Density 0.001%

    No Known Activations