© 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. 5233
    Prev
    Next
    INDEX
    Explanations

    terms related to financial institutions and bankruptcy proceedings

    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
    eldon
    -0.10
     EÅŁ
    -0.08
    ynes
    -0.08
    ãĤ·ãĤ§
    -0.07
    ?family
    -0.07
     леÑģ
    -0.07
    ãĤ¤ãĥ¤
    -0.07
    ViewItem
    -0.07
    aptop
    -0.07
    برÛĮ
    -0.07
    POSITIVE LOGITS
     enforcing
    0.08
     enforce
    0.08
     exercise
    0.07
     demand
    0.06
     demanding
    0.06
     enforcement
    0.06
     exerc
    0.06
    294
    0.06
    umer
    0.06
     enforced
    0.06
    Activations Density 0.015%

    No Known Activations