© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 25-LLAMASCOPE-RES-32K
    11. 15078
    Prev
    Next
    INDEX
    Explanations

    references to celebrations and commemorations, particularly in the context of anniversaries and events supporting social causes

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    окон
    -0.17
     götür
    -0.15
    ãĥ³ãĥĪ
    -0.15
    adero
    -0.14
    andbox
    -0.13
    okoj
    -0.13
    ัà¹ī
    -0.13
     zá
    -0.12
    ys
    -0.12
    ç§Ģ
    -0.12
    POSITIVE LOGITS
     celebration
    0.51
     celebrations
    0.47
     celebrate
    0.44
    cele
    0.44
     celebr
    0.43
     celebrating
    0.42
    åºĨ
    0.42
     Celebr
    0.41
     anniversary
    0.41
     celebrates
    0.39
    Activations Density 0.293%

    No Known Activations