© 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. 88881
    Prev
    Next
    INDEX
    Explanations

    concepts related to environmental impact 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
     Cop
    -0.07
    yg
    -0.06
     libs
    -0.06
    ITO
    -0.06
     Cong
    -0.06
    hung
    -0.05
    UILD
    -0.05
    wendung
    -0.05
    azor
    -0.05
     Pale
    -0.05
    POSITIVE LOGITS
    Ïģιά
    0.07
     schop
    0.07
    ëĿ¼ëĬĶ
    0.06
    éĢĢ
    0.06
    лиÑĩ
    0.06
    象
    0.06
    ëįķ
    0.06
    ีà¹Ģม
    0.06
    æŁ»
    0.06
    aits
    0.06
    Activations Density 0.008%

    No Known Activations