© 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. 5447
    Prev
    Next
    INDEX
    Explanations

    mentions of the SEC (Securities and Exchange Commission) and its related activities concerning financial regulations

    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
    åĢij
    -0.07
    æł·çļĦ
    -0.07
    æĮ¯ãĤĬ
    -0.07
    ÑģÑĤанов
    -0.07
     pul
    -0.07
    è¾ij
    -0.06
    aeda
    -0.06
    سÙĪب
    -0.06
    IDEOS
    -0.06
    istrovstvÃŃ
    -0.06
    POSITIVE LOGITS
    .gov
    0.10
    tember
    0.07
    (OS
    0.07
    URITY
    0.07
    rieve
    0.07
    gov
    0.07
    igon
    0.06
    otta
    0.06
    405
    0.06
    argo
    0.06
    Activations Density 0.002%

    No Known Activations