© 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. 28342
    Prev
    Next
    INDEX
    Explanations

    references to time and comparison

    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
    kin
    -0.08
    kn
    -0.07
    озможно
    -0.06
     sez
    -0.06
     yaz
    -0.06
    otton
    -0.06
    اغ
    -0.06
    ิมà¸ŀ
    -0.06
     éĻ
    -0.05
    unique
    -0.05
    POSITIVE LOGITS
     comparison
    0.10
    comparison
    0.08
     Comparison
    0.08
     Compare
    0.07
     comparator
    0.07
    ispiel
    0.07
     comparisons
    0.07
    _comparison
    0.07
     transformation
    0.07
    compare
    0.07
    Activations Density 0.013%

    No Known Activations