© 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. 2547
    Prev
    Next
    INDEX
    Explanations

    numerical data related to scores or performance metrics

    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
    iasi
    -0.07
    баÑĩ
    -0.06
    95
    -0.06
    ipheral
    -0.06
     vit
    -0.06
    iew
    -0.06
    ارÙģ
    -0.06
    ее
    -0.06
    tolower
    -0.06
     symbolic
    -0.06
    POSITIVE LOGITS
     Byl
    0.07
    اضÙĬ
    0.06
    addock
    0.06
     tarz
    0.06
    ãģ
    0.06
    utra
    0.06
    à¸Ļà¸ģ
    0.06
    é§
    0.06
     MyApp
    0.06
    uhn
    0.06
    Activations Density 0.001%

    No Known Activations