© 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. 41128
    Prev
    Next
    INDEX
    Explanations

    code file references and their corresponding line numbers in Java programming related to Android development

    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
    egis
    -0.07
    ÙħاÙħ
    -0.07
    ÅŁÄ±
    -0.07
    roys
    -0.07
    ropa
    -0.07
    roids
    -0.07
    isses
    -0.07
    ½Ķ
    -0.07
    aģı
    -0.06
    ео
    -0.06
    POSITIVE LOGITS
    OLEAN
    0.06
    BOOLE
    0.06
    ModelProperty
    0.06
    ãĥ³ãĤ¹
    0.06
    æ¡£
    0.06
    ICA
    0.06
     Brief
    0.05
    Brief
    0.05
    opper
    0.05
    undy
    0.05
    Activations Density 0.002%

    No Known Activations