© 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. 106316
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to fluid dynamics and environmental science

    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
     Progress
    -0.07
    :
    -0.07
    ,
    -0.07
     progress
    -0.07
    -0.06
    [
    -0.06
    è§Ĵ
    -0.06
    оÑģÑĮ
    -0.05
    .
    -0.05
    ero
    -0.05
    POSITIVE LOGITS
     layer
    0.12
     layers
    0.12
     zones
    0.11
     zone
    0.11
    層
    0.11
    ayer
    0.10
    layer
    0.10
     Zone
    0.10
     regions
    0.09
     Layer
    0.09
    Activations Density 0.048%

    No Known Activations