© 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. 15-LLAMASCOPE-RES-32K
    11. 2573
    Prev
    Next
    INDEX
    Explanations

    references to companies and brands, primarily focusing on technology and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    allet
    -0.20
    алÑİ
    -0.17
    /write
    -0.17
    well
    -0.17
     unw
    -0.17
     unwilling
    -0.17
     wastewater
    -0.16
     widely
    -0.16
    *width
    -0.16
    åĢij
    -0.16
    POSITIVE LOGITS
    nesday
    0.22
    robe
    0.19
    ASHINGTON
    0.18
    NES
    0.17
    ondrous
    0.17
    اسطة
    0.17
    haven
    0.17
    ür
    0.16
    avelength
    0.16
    ograd
    0.16
    Activations Density 1.319%

    No Known Activations