© 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. 119321
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulatory actions and trade restrictions

    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
    RTC
    -0.06
    assin
    -0.06
     Cass
    -0.06
    ass
    -0.06
    .sources
    -0.06
     hearing
    -0.06
    abad
    -0.06
    uries
    -0.06
     BUG
    -0.06
    .Skin
    -0.06
    POSITIVE LOGITS
    ãĥ¼ãĤº
    0.07
    eneric
    0.07
    èĤ¥
    0.06
    Specifier
    0.06
    izr
    0.06
    -any
    0.06
    ̣
    0.06
    ivo
    0.06
    obao
    0.06
     touching
    0.06
    Activations Density 0.008%

    No Known Activations