© 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. 15172
    Prev
    Next
    INDEX
    Explanations

    financial transactions and their impact on the economy

    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
     Lent
    -0.07
    lder
    -0.07
     Forum
    -0.07
    resh
    -0.06
    ifetime
    -0.06
    stra
    -0.06
     CommandLine
    -0.06
     forum
    -0.06
     lease
    -0.06
    607
    -0.06
    POSITIVE LOGITS
     rem
    0.08
    empo
    0.08
    demo
    0.07
     transc
    0.07
     trans
    0.07
     demo
    0.07
     Trans
    0.07
     Demo
    0.07
    ocre
    0.07
    _migration
    0.07
    Activations Density 0.005%

    No Known Activations