© 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 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. 88925
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to financial assistance and loan forgiveness programs

    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
    ãĥ¡ãĥ©
    -0.07
    ificador
    -0.07
    gtest
    -0.07
    ipherals
    -0.06
    mainwindow
    -0.06
    odule
    -0.06
    пов
    -0.06
    FIELDS
    -0.06
    ısından
    -0.06
     Bust
    -0.06
    POSITIVE LOGITS
     certain
    0.09
     Certain
    0.07
     whenever
    0.07
     Pert
    0.06
    enever
    0.06
    omid
    0.06
     Rede
    0.06
    Certain
    0.06
    üml
    0.06
     among
    0.06
    Activations Density 0.021%

    No Known Activations