© 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. 28-LLAMASCOPE-RES-32K
    11. 22532
    Prev
    Next
    INDEX
    Explanations

    references to time and events, particularly focusing on significant occurrences such as deaths, festivals, and weekly activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mon
    -0.35
     Mondays
    -0.33
     Tues
    -0.29
     MON
    -0.28
     Mon
    -0.28
    Tuesday
    -0.27
     Wed
    -0.27
    mon
    -0.27
     Tue
    -0.27
     Sundays
    -0.26
    POSITIVE LOGITS
     Friday
    0.98
    Friday
    0.91
     Fri
    0.85
     friday
    0.80
    Fri
    0.78
     Fridays
    0.69
     fri
    0.61
     Saturday
    0.56
    Saturday
    0.52
    riday
    0.50
    Activations Density 0.104%

    No Known Activations