© 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. 128818
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to bankruptcy and financial transactions

    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
    \views
    -0.08
     retali
    -0.07
    orado
    -0.07
    quina
    -0.07
    ãĥ©ãĤ¤ãĥ³
    -0.07
    iais
    -0.07
     bri
    -0.07
    ngr
    -0.07
    اص
    -0.07
    ContextHolder
    -0.07
    POSITIVE LOGITS
     assets
    0.10
     liquid
    0.10
     Liquid
    0.09
     Assets
    0.09
    assets
    0.07
    liquid
    0.07
     asset
    0.07
    -assets
    0.07
     bankruptcy
    0.07
     insol
    0.07
    Activations Density 0.034%

    No Known Activations