© 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. 40951
    Prev
    Next
    INDEX
    Explanations

    references to meteorological patterns and phenomena

    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
    .addHandler
    -0.07
    istrat
    -0.07
    naÄį
    -0.07
    mutations
    -0.06
    hea
    -0.06
    abus
    -0.06
    aque
    -0.06
    itrust
    -0.06
    ittings
    -0.06
    /logs
    -0.06
    POSITIVE LOGITS
     conv
    0.07
    LOB
    0.06
    gers
    0.06
    -Men
    0.06
     Barry
    0.06
    das
    0.06
    Conv
    0.06
    alled
    0.06
    441
    0.06
     atl
    0.05
    Activations Density 0.022%

    No Known Activations