© 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. 75989
    Prev
    Next
    INDEX
    Explanations

    mentions of environmental issues and the impact on water systems

    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
     norge
    -0.07
    Parsed
    -0.06
    ÏĨο
    -0.06
     pros
    -0.06
     parch
    -0.06
     sleep
    -0.06
     Forrest
    -0.06
    ÑĨин
    -0.06
     cic
    -0.06
    piler
    -0.06
    POSITIVE LOGITS
    ewater
    0.09
     Clean
    0.08
     Ches
    0.07
     sew
    0.07
     Cleaner
    0.07
     Sew
    0.07
    eut
    0.07
    otts
    0.07
     Newtown
    0.07
    anel
    0.07
    Activations Density 0.046%

    No Known Activations