© 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. 23-LLAMASCOPE-RES-32K
    11. 31246
    Prev
    Next
    INDEX
    Explanations

    references to structured events and schedules, particularly in relation to conferences and school

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     May
    -0.29
     æĺ¥
    -0.28
     Christmas
    -0.28
    May
    -0.28
    Christmas
    -0.27
     spring
    -0.27
    April
    -0.27
    æĺ¥
    -0.27
     Easter
    -0.26
     christmas
    -0.26
    POSITIVE LOGITS
     Sept
    0.70
    Sept
    0.63
     September
    0.63
    September
    0.62
     Aug
    0.58
     August
    0.57
     Sep
    0.57
    August
    0.56
     sept
    0.55
    Aug
    0.54
    Activations Density 0.284%

    No Known Activations