© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 1342
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to modeling, design, and noise in simulations

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

    Technical terms used in scientific contexts, especially referring to specific components, measurements, or artifacts in technical systems like laser optics, BIM files, software modules, and simulation models.

    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
    stadt
    -0.07
    emory
    -0.07
    alex
    -0.06
    ozo
    -0.06
    hammad
    -0.06
    astic
    -0.06
    byn
    -0.06
    ago
    -0.06
    aget
    -0.06
    tal
    -0.06
    POSITIVE LOGITS
    Ø´ÙĪØ±
    0.07
    830
    0.07
    бÑĥдÑĮ
    0.07
    InitStruct
    0.06
    _TypeDef
    0.06
    BuilderInterface
    0.06
    âĢĮÙĨ
    0.06
    ноÑģи
    0.06
    *>*
    0.06
    AssignableFrom
    0.06
    Activations Density 0.240%

    No Known Activations