© 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. 85182
    Prev
    Next
    INDEX
    Explanations

    concepts related to synchronization in complex networks

    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
    afa
    -0.07
     Serial
    -0.06
    tre
    -0.06
    oran
    -0.06
    uras
    -0.06
     Tre
    -0.06
     forfe
    -0.05
     cub
    -0.05
    ä¹ĭä¸Ģ
    -0.05
    nek
    -0.05
    POSITIVE LOGITS
    ãģªãģijãĤĮãģ°
    0.08
    Ľå»º
    0.08
    ourke
    0.08
    incip
    0.07
    ICODE
    0.07
     Occ
    0.07
    usc
    0.07
     actually
    0.06
    indow
    0.06
    ÏĥÏĦαν
    0.06
    Activations Density 0.040%

    No Known Activations