© 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. 15-LLAMASCOPE-RES-131K
    11. 88038
    Prev
    Next
    INDEX
    Explanations

    phrases that express components of sustainability and environmental consciousness

    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
    ÏĢα
    -0.08
    ism
    -0.08
    ville
    -0.07
    .FontStyle
    -0.07
    ase
    -0.07
    iness
    -0.07
    imli
    -0.07
    avit
    -0.07
    orem
    -0.06
    itÃł
    -0.06
    POSITIVE LOGITS
     circumstances
    0.06
     Labs
    0.06
     Walk
    0.06
     labs
    0.06
     lab
    0.06
     times
    0.06
     ÙħØ®
    0.06
     vezes
    0.06
    ÑĥÑģка
    0.06
    ouser
    0.06
    Activations Density 0.005%

    No Known Activations