© 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. 93307
    Prev
    Next
    INDEX
    Explanations

    references to financial transactions or payments

    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
    CTX
    -0.06
    大人
    -0.06
     ÑģÑĤаÑĢи
    -0.06
     civilians
    -0.06
     human
    -0.06
    ãģĤãģĴ
    -0.06
    esen
    -0.06
     nett
    -0.06
    emark
    -0.05
     Human
    -0.05
    POSITIVE LOGITS
     recep
    0.07
    ượt
    0.06
    thresh
    0.06
     NOI
    0.06
    corn
    0.06
    _enter
    0.06
    AppDelegate
    0.06
    üre
    0.06
    íĬ
    0.06
     knots
    0.06
    Activations Density 0.000%

    No Known Activations