© 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. 15-LLAMASCOPE-RES-131K
    11. 384
    Prev
    Next
    INDEX
    Explanations

    references to project management tools and features

    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
    MainThread
    -0.07
    ãģĵãĤĵ
    -0.07
    è¾ŀ
    -0.07
    ERM
    -0.07
     ç¿
    -0.06
    jvu
    -0.06
    رب
    -0.06
    foy
    -0.06
    NECT
    -0.06
     dö
    -0.06
    POSITIVE LOGITS
     project
    0.07
     work
    0.07
     progress
    0.07
     Work
    0.07
     projects
    0.07
     eta
    0.07
     Projects
    0.06
    projects
    0.06
    èo
    0.06
    ects
    0.06
    Activations Density 0.007%

    No Known Activations