© 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. 17-LLAMASCOPE-RES-131K
    11. 70558
    Prev
    Next
    INDEX
    Explanations

    different operational modes of a system or device

    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
    们
    -0.07
    utral
    -0.07
    åĢij
    -0.07
    uya
    -0.07
    imals
    -0.07
    åĪ°çļĦ
    -0.07
    ouis
    -0.07
    relude
    -0.07
    ̧
    -0.07
    ago
    -0.07
    POSITIVE LOGITS
     mode
    0.07
    imli
    0.07
     Hann
    0.07
     Kurt
    0.06
    amento
    0.06
    ű
    0.06
    ạn
    0.06
    liness
    0.06
    771
    0.05
    GMEM
    0.05
    Activations Density 0.021%

    No Known Activations