© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118339
    Prev
    Next
    INDEX
    Explanations

    references to artistic tributes or recognitions

    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
     Spir
    -0.07
    본
    -0.07
    ilet
    -0.07
     eskort
    -0.07
    iams
    -0.07
    วà¸Ļ
    -0.07
     prez
    -0.06
    ï½¢
    -0.06
    cky
    -0.06
     æĹ¥æľŁ
    -0.06
    POSITIVE LOGITS
     now
    0.12
     suddenly
    0.10
    now
    0.09
     became
    0.08
     Now
    0.08
     become
    0.08
     finally
    0.08
     actually
    0.07
     becomes
    0.07
    uddenly
    0.07
    Activations Density 0.028%

    No Known Activations