© 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. 86851
    Prev
    Next
    INDEX
    Explanations

    references to time periods, specifically seasons and years

    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
     Sin
    -0.06
    rint
    -0.06
    IBE
    -0.06
     rival
    -0.06
     alternatives
    -0.06
    .si
    -0.06
     sin
    -0.06
    arius
    -0.06
     Calvin
    -0.06
     workers
    -0.05
    POSITIVE LOGITS
    201
    0.10
    202
    0.09
    itta
    0.07
    .datatables
    0.07
    itz
    0.07
    Interop
    0.07
    _decor
    0.07
    engo
    0.07
    uml
    0.07
    udder
    0.07
    Activations Density 0.009%

    No Known Activations