© 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. 40888
    Prev
    Next
    INDEX
    Explanations

    times of day, specifically focusing on AM and PM designations

    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
    iken
    -0.07
    amt
    -0.06
    athan
    -0.06
    abic
    -0.06
    kek
    -0.06
    ÏĦα
    -0.06
    vis
    -0.06
    ocket
    -0.06
    yy
    -0.06
     Hus
    -0.06
    POSITIVE LOGITS
     ET
    0.08
    /pm
    0.07
    CNT
    0.07
     Barton
    0.07
     OD
    0.07
    tember
    0.06
    æĸ¹
    0.06
    ABCDEFGHIJKLMNOP
    0.06
    Detach
    0.06
     pst
    0.06
    Activations Density 0.006%

    No Known Activations