© 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. 9-LLAMASCOPE-RES-131K
    11. 97833
    Prev
    Next
    INDEX
    Explanations

    programmatic references to asset management and resource handling in code

    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
    aç
    -0.07
    itable
    -0.06
    emouth
    -0.06
    986
    -0.06
    nty
    -0.06
    DOMContentLoaded
    -0.06
    891
    -0.06
    utow
    -0.06
    ifix
    -0.06
    835
    -0.06
    POSITIVE LOGITS
    udit
    0.07
    elas
    0.07
    δÏĮν
    0.07
    LATED
    0.06
    лаз
    0.06
    ãĥ¼ãĥª
    0.06
    ãĥ©ãĤ¹
    0.06
    ="../../../
    0.06
    iah
    0.06
     бÑĸ
    0.06
    Activations Density 0.031%

    No Known Activations