© 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. 83637
    Prev
    Next
    INDEX
    Explanations

    phrases related to improving lives and fostering community development

    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
     Hoch
    -0.07
    iba
    -0.06
    aled
    -0.06
     عÙĪ
    -0.06
    thon
    -0.06
    Äħż
    -0.06
     oder
    -0.06
    och
    -0.06
    eldon
    -0.06
    520
    -0.06
    POSITIVE LOGITS
     пÑĥÑĤем
    0.14
     ÑĪлÑıÑħом
    0.12
     mediante
    0.11
    sthrough
    0.11
     through
    0.11
     prostÅĻednictvÃŃm
    0.11
    through
    0.10
     THROUGH
    0.10
     bằng
    0.10
     via
    0.09
    Activations Density 0.035%

    No Known Activations