© 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. 17-LLAMASCOPE-RES-131K
    6. 88024
    Prev
    Next
    INDEX
    Explanations

    concepts related to transient experiences and impermanence

    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
    ÃŃch
    -0.07
    輪
    -0.07
    ãĥ³ãĥĦ
    -0.07
    .lazy
    -0.07
    metric
    -0.06
    yaw
    -0.06
    ãģĦãĤĦ
    -0.06
     yıldır
    -0.06
    buie
    -0.06
    Lazy
    -0.06
    POSITIVE LOGITS
     temporary
    0.18
     Temporary
    0.15
    temporary
    0.15
     transient
    0.15
    Temporary
    0.14
     only
    0.14
     brief
    0.13
     limited
    0.13
     lasted
    0.13
     lasts
    0.13
    Activations Density 0.175%

    No Known Activations