© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 28680
    Prev
    Next
    INDEX
    Explanations

    references to international matters and global perspectives

    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
    _MPI
    -0.07
    fak
    -0.07
    ikk
    -0.07
    asti
    -0.07
    ilden
    -0.07
    oland
    -0.07
    uries
    -0.07
    ãĤĵãģ¨
    -0.07
     ApplicationController
    -0.06
    aticon
    -0.06
    POSITIVE LOGITS
     foreign
    0.07
     Affairs
    0.07
    /local
    0.07
    _foreign
    0.07
     affairs
    0.07
    foreign
    0.06
     aspects
    0.06
    å¤ı
    0.06
     abroad
    0.06
     SCM
    0.06
    Activations Density 0.017%

    No Known Activations