© 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. 15-LLAMASCOPE-RES-131K
    11. 90373
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "What is the."

    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
    uler
    -0.06
    ä½ĵ
    -0.06
     Cah
    -0.06
    plotlib
    -0.06
    athe
    -0.06
     whistle
    -0.05
     nowhere
    -0.05
     har
    -0.05
     McConnell
    -0.05
     Bent
    -0.05
    POSITIVE LOGITS
    ugi
    0.08
    egov
    0.07
    á»ij
    0.07
    ynos
    0.07
    едак
    0.07
    iao
    0.07
     доÑģÑĤ
    0.07
    otron
    0.07
    craper
    0.07
    ANDOM
    0.07
    Activations Density 0.003%

    No Known Activations