© 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 EvalsExportsinterp-engineNEWAPI 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. 31020
    Prev
    Next
    INDEX
    Explanations

    concepts related to environmental awareness and sustainability

    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
    uyen
    -0.07
    .sys
    -0.07
    istributed
    -0.06
    úb
    -0.06
     Fluent
    -0.06
     extern
    -0.06
    203
    -0.06
    iao
    -0.06
    ongan
    -0.06
    ereotype
    -0.06
    POSITIVE LOGITS
    人们
    0.07
     modern
    0.06
    æį·
    0.06
    everyone
    0.06
     globalization
    0.06
    dub
    0.06
    볤
    0.06
    åĨ
    0.06
    以æĿ¥
    0.06
    rame
    0.06
    Activations Density 0.052%

    No Known Activations