© 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. 61013
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional situations and uncertainties

    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
     aston
    -0.06
    isé
    -0.06
    anted
    -0.06
    ITTER
    -0.06
    aneously
    -0.06
    uden
    -0.06
    Äįky
    -0.06
    ancode
    -0.06
    Å¡it
    -0.06
    isy
    -0.06
    POSITIVE LOGITS
     seri
    0.06
    å¤ķ
    0.06
    erez
    0.06
    essler
    0.06
    ulton
    0.06
    uren
    0.06
    894
    0.06
    ìĶ
    0.06
    ContentSize
    0.06
     Roots
    0.06
    Activations Density 0.006%

    No Known Activations