© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 16955
    Prev
    Next
    INDEX
    Explanations

    references to stud welding systems and related machinery

    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
     format
    -0.06
     structure
    -0.06
     veri
    -0.06
    ulumi
    -0.06
     correct
    -0.06
    å§Ķåĵ¡
    -0.06
     mood
    -0.05
     Structure
    -0.05
     exercise
    -0.05
     contents
    -0.05
    POSITIVE LOGITS
    apro
    0.08
     productivity
    0.07
     olduk
    0.07
    IPA
    0.07
    abort
    0.07
    _macros
    0.07
    æ¥Ń
    0.07
    udas
    0.07
    ç«Ļ
    0.06
    serter
    0.06
    Activations Density 0.022%

    No Known Activations