© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 82037
    Prev
    Next
    INDEX
    Explanations

    metrics or statistics related to user engagement or download numbers

    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
    aryl
    -0.06
    ConfigurationException
    -0.06
    otu
    -0.06
     Basket
    -0.06
    atham
    -0.06
    amber
    -0.06
    oref
    -0.06
    ιÏİ
    -0.06
     ÙĪا
    -0.06
     componentName
    -0.06
    POSITIVE LOGITS
     daily
    0.09
     users
    0.09
    daily
    0.09
     user
    0.08
    users
    0.08
     usage
    0.08
     global
    0.07
    growth
    0.07
     growth
    0.07
    .daily
    0.07
    Activations Density 0.019%

    No Known Activations