© 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. 83455
    Prev
    Next
    INDEX
    Explanations

    references to the history and development of aviation technology

    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
    etsk
    -0.08
    eam
    -0.07
    ê·¼
    -0.06
    енÑĤа
    -0.06
    æ»ħ
    -0.06
    leton
    -0.06
     Ùģض
    -0.06
    ervas
    -0.06
     isr
    -0.06
    anzi
    -0.06
    POSITIVE LOGITS
     launch
    0.09
     launching
    0.07
    ä¿
    0.07
    -launch
    0.07
    akeup
    0.07
    etler
    0.07
     phóng
    0.07
    launch
    0.07
    iler
    0.07
     umb
    0.07
    Activations Density 0.020%

    No Known Activations