© 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. 5-LLAMASCOPE-RES-131K
    11. 126737
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of time

    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
    oki
    -0.07
    asy
    -0.06
    itzer
    -0.06
    ia
    -0.06
    ellig
    -0.06
    ijo
    -0.06
    ifiable
    -0.05
    jde
    -0.05
    iah
    -0.05
    Å¡tÃŃ
    -0.05
    POSITIVE LOGITS
    utto
    0.07
    alles
    0.07
    bart
    0.07
    eyse
    0.07
    sing
    0.07
    ighet
    0.06
    inalg
    0.06
    -angular
    0.06
    mekte
    0.06
    HAV
    0.06
    Activations Density 0.004%

    No Known Activations