© 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. 41292
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to operations and installations

    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
    ÙĪار
    -0.07
    aji
    -0.07
    ascus
    -0.06
    åĬŀ
    -0.06
    /Internal
    -0.06
    gregation
    -0.06
    Goods
    -0.06
     rub
    -0.06
     Brace
    -0.06
     duy
    -0.06
    POSITIVE LOGITS
     installs
    0.07
     customers
    0.07
     installations
    0.07
     deployments
    0.07
    yg
    0.07
     customer
    0.07
     install
    0.07
     already
    0.07
    uzzer
    0.07
     client
    0.06
    Activations Density 0.022%

    No Known Activations