© 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. 18-LLAMASCOPE-RES-32K
    11. 9043
    Prev
    Next
    INDEX
    Explanations

    phrases that signify interactions and relationships

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    emas
    -0.16
    =$('#
    -0.14
    áj
    -0.14
    UTO
    -0.13
    sko
    -0.13
    iesz
    -0.13
    anou
    -0.13
    iloc
    -0.12
    .ping
    -0.12
    нÑĸвеÑĢ
    -0.12
    POSITIVE LOGITS
    apos
    0.13
    .sidebar
    0.12
     Rag
    0.12
    Ø°ÛĮر
    0.12
    Ìģ
    0.12
     fgets
    0.12
    Ā
    0.11
     fitte
    0.11
     Gates
    0.11
    hare
    0.11
    Activations Density 4.092%

    No Known Activations