© 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. 15064
    Prev
    Next
    INDEX
    Explanations

    terms related to health systems and public services

    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
    -IN
    -0.15
    anzi
    -0.14
     thereof
    -0.14
    357
    -0.13
    ucc
    -0.12
    _rl
    -0.12
    å¥ī
    -0.12
    legg
    -0.12
    blr
    -0.11
    Ỽi
    -0.11
    POSITIVE LOGITS
     in
    0.54
    åľ¨
    0.41
    à¹ĥà¸Ļ
    0.38
     în
    0.37
     ÙģÙĬ
    0.37
     ÏĥÏĦην
    0.36
     åľ¨
    0.35
     trong
    0.34
     nella
    0.33
     ợ
    0.33
    Activations Density 3.246%

    No Known Activations