© 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. 2793
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to audio processing and database systems

    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
     either
    -0.06
    ниÑı
    -0.06
     be
    -0.05
     anymore
    -0.05
    vido
    -0.05
     CURL
    -0.05
     phen
    -0.05
     dere
    -0.05
     no
    -0.05
     respectively
    -0.05
    POSITIVE LOGITS
     же
    0.11
     ayrıca
    0.11
    â̦↵↵↵
    0.09
     ÙĩÙħÚĨÙĨÛĮÙĨ
    0.09
     ëĺIJíķľ
    0.09
    주ëĬĶ
    0.09
    odore
    0.09
    è¿Ļç§į
    0.08
     â̦↵↵
    0.08
    uxtap
    0.08
    Activations Density 0.110%

    No Known Activations