© 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. 125090
    Prev
    Next
    INDEX
    Explanations

    Java dependency injection related terms and annotations

    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
    ingo
    -0.08
    azen
    -0.08
    edic
    -0.07
    dür
    -0.07
    elled
    -0.07
    mitt
    -0.07
    گاب
    -0.07
    è½
    -0.07
    ifter
    -0.07
     //!<
    -0.07
    POSITIVE LOGITS
    برÛĮ
    0.07
    رÙĥ
    0.06
    ¿
    0.06
    าà¸
    0.06
    oucher
    0.06
    artz
    0.05
    otec
    0.05
    rán
    0.05
     Prest
    0.05
    chia
    0.05
    Activations Density 0.000%

    No Known Activations