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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 128518
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced material manufacturing and design processes

    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
     ayr
    -0.08
    neutral
    -0.07
    .volley
    -0.07
    illis
    -0.07
    åĬ¿
    -0.07
    estre
    -0.07
    ãĤ¤ãĥ¤
    -0.07
    اÛĮØ´
    -0.07
    /assert
    -0.07
     ÄĮer
    -0.07
    POSITIVE LOGITS
     Complex
    0.07
     finished
    0.07
     complicated
    0.07
     intricate
    0.07
    件
    0.07
     complex
    0.07
     prototypes
    0.06
     Complexity
    0.06
     Airways
    0.06
     precision
    0.06
    Activations Density 0.016%

    No Known Activations