© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3665
    Prev
    Next
    INDEX
    Explanations

    references to electrical wiring and connections

    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
    agna
    -0.08
    ucci
    -0.07
    ottle
    -0.06
    ConnectionString
    -0.06
    apos
    -0.06
     variant
    -0.06
    optera
    -0.06
    338
    -0.06
    inness
    -0.06
    pod
    -0.06
    POSITIVE LOGITS
    iae
    0.07
    jak
    0.07
     Ung
    0.07
    éĴ®
    0.07
    #ad
    0.06
    istine
    0.06
    FileManager
    0.06
    0.06
    lero
    0.06
     çünkü
    0.06
    Activations Density 0.002%

    No Known Activations