© 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. 17-LLAMASCOPE-RES-131K
    11. 130036
    Prev
    Next
    INDEX
    Explanations

    key phrases related to compliance and 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
     passe
    -0.07
    GIS
    -0.06
    ugg
    -0.06
     privat
    -0.06
     Rhino
    -0.06
    CHIP
    -0.06
    enne
    -0.06
    foil
    -0.06
    enge
    -0.06
    ãĢ
    -0.06
    POSITIVE LOGITS
     regulator
    0.06
    thon
    0.06
     UIG
    0.06
     proprietor
    0.06
    apis
    0.06
     rout
    0.06
     Parade
    0.06
    sie
    0.06
    ande
    0.06
     boz
    0.06
    Activations Density 0.000%

    No Known Activations