© 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 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. 57339
    Prev
    Next
    INDEX
    Explanations

    Java-specific class and method references related to Android UI components

    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
    uchen
    -0.07
    ranÃŃ
    -0.07
    bai
    -0.07
    uil
    -0.07
    ëıĻ
    -0.06
    ecta
    -0.06
    uche
    -0.06
    ench
    -0.06
    engin
    -0.06
    Sharper
    -0.06
    POSITIVE LOGITS
    orum
    0.06
    ãĥ³ãĤ¬
    0.06
     rol
    0.06
     Mo
    0.06
    Ñĵ
    0.06
    571
    0.06
     Druid
    0.05
    821
    0.05
    <TResult
    0.05
    ánt
    0.05
    Activations Density 0.002%

    No Known Activations