© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 103881
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and code-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Words or phrases appearing within specific contexts across different text types, including programming code comments, technical documentation, and web content. Many instances show programming-related markers (like function parameters or variable names), navigation instructions in documentation ("by selecting"), conditional statements ("when", "might"), or technical content elements ("positions", "jet", "hub", "sub", "mix").

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    elf
    -0.06
    alf
    -0.06
    adelphia
    -0.06
    еÑĤÑĮÑģÑı
    -0.06
    erson
    -0.06
    actus
    -0.06
    ÑĦÑĸ
    -0.06
     Hoy
    -0.06
    lett
    -0.05
    ama
    -0.05
    POSITIVE LOGITS
    bing
    0.08
    ing
    0.08
    инг
    0.07
    eking
    0.07
    printStats
    0.07
     yaÅŁayan
    0.07
    çĽijåIJ¬é¡µéĿ¢
    0.07
    TING
    0.07
    ding
    0.07
     DISCLAIM
    0.07
    Activations Density 0.107%

    No Known Activations