© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 88932
    Prev
    Next
    INDEX
    Explanations

    phrases related to compliance and requirements for applications

    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
    ophobia
    -0.08
    ason
    -0.07
    оÑģÑĤÑĥп
    -0.07
    amedi
    -0.07
     Wass
    -0.07
    hell
    -0.07
    readcr
    -0.07
    ncy
    -0.07
    inki
    -0.06
    ofire
    -0.06
    POSITIVE LOGITS
     unless
    0.12
     anymore
    0.11
    unless
    0.09
     altogether
    0.09
    ero
    0.07
     vůbec
    0.07
     Unless
    0.07
    itar
    0.07
     necessarily
    0.07
     nor
    0.06
    Activations Density 0.023%

    No Known Activations