© 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. 128815
    Prev
    Next
    INDEX
    Explanations

    references to tax forms and income reporting in financial contexts

    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
    ipc
    -0.07
    ouden
    -0.06
    bic
    -0.06
     huy
    -0.06
     fund
    -0.06
     tÆ°Æ¡i
    -0.06
    Store
    -0.06
    ILT
    -0.06
    /gcc
    -0.06
     Riy
    -0.06
    POSITIVE LOGITS
    kening
    0.08
    gross
    0.08
     gross
    0.07
    aldo
    0.07
    .beginTransaction
    0.07
    LocalizedMessage
    0.07
    Äįan
    0.06
    udoku
    0.06
     Gross
    0.06
    ucher
    0.06
    Activations Density 0.006%

    No Known Activations