© 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. 15-LLAMASCOPE-RES-131K
    11. 104411
    Prev
    Next
    INDEX
    Explanations

    instances of commas and pauses in the text

    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
    ound
    -0.08
    enberg
    -0.08
    ë¡Ŀ
    -0.08
     besten
    -0.07
    ä¹ĭä¸Ģ
    -0.07
    .Reporting
    -0.07
    åķ
    -0.07
    одейÑģÑĤв
    -0.07
    STYPE
    -0.07
    iegel
    -0.07
    POSITIVE LOGITS
     our
    0.06
     provider
    0.06
    roupe
    0.06
     pur
    0.06
     capital
    0.06
     former
    0.06
     gra
    0.06
     another
    0.05
     god
    0.05
    igrams
    0.05
    Activations Density 0.301%

    No Known Activations