© 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. 127784
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulatory compliance and environmental assessments

    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
     зада
    -0.06
     æ¥
    -0.06
     ware
    -0.06
     Survivor
    -0.06
    ANNOT
    -0.06
    ONGL
    -0.06
     Crawford
    -0.06
     UNS
    -0.06
    agnar
    -0.06
    ÙĤÙĬ
    -0.05
    POSITIVE LOGITS
     environmental
    0.10
    environment
    0.08
     Environmental
    0.08
    Environmental
    0.08
     project
    0.07
     Consultants
    0.07
    oux
    0.07
    ensburg
    0.07
    /environment
    0.07
    vironment
    0.07
    Activations Density 0.029%

    No Known Activations