© 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. 62184
    Prev
    Next
    INDEX
    Explanations

    references to taxes, fees, and related financial charges

    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
    ajan
    -0.07
    838
    -0.06
    uard
    -0.06
    juven
    -0.06
    zeichnet
    -0.06
     Casc
    -0.06
    weise
    -0.06
    νοι
    -0.06
    aj
    -0.06
    .interfaces
    -0.06
    POSITIVE LOGITS
    gst
    0.06
     taxes
    0.06
    ller
    0.06
    strup
    0.06
     final
    0.06
    uros
    0.06
    wargs
    0.06
     charges
    0.06
    oft
    0.06
    imps
    0.06
    Activations Density 0.011%

    No Known Activations