© 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. 82376
    Prev
    Next
    INDEX
    Explanations

    landmarks and notable geographical features

    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
    steen
    -0.07
    ãĤ¹ãĥļ
    -0.06
    è¶Ĭ
    -0.06
    OG
    -0.06
    enz
    -0.06
    ستÙĩ
    -0.06
    ensa
    -0.06
    ëŁŃ
    -0.06
    оÑī
    -0.06
    COMPARE
    -0.06
    POSITIVE LOGITS
     world
    0.08
     اÙĦعاÙĦÙħ
    0.07
    åĸ®
    0.07
    aria
    0.06
    ä¸ĸçķĮ
    0.06
     recorded
    0.06
     worldwide
    0.06
     World
    0.06
    zik
    0.06
    usal
    0.06
    Activations Density 0.031%

    No Known Activations