© 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. 61629
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives that emphasize quality or significance

    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
    owi
    -0.08
    arently
    -0.07
    rug
    -0.07
    ivor
    -0.07
    ORE
    -0.07
    iens
    -0.07
     Kaynak
    -0.07
    oser
    -0.06
    usu
    -0.06
    Ä±ÅŁÄ±k
    -0.06
    POSITIVE LOGITS
    åIJ§
    0.07
     ought
    0.07
     slightly
    0.06
     пÑĢидеÑĤÑģÑı
    0.06
    ãĤĤãģ£ãģ¨
    0.06
    ICATION
    0.06
     ÙĬÙĥÙĪÙĨ
    0.06
    Prostit
    0.06
     most
    0.06
     fairly
    0.05
    Activations Density 0.038%

    No Known Activations