© 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. 31-LLAMASCOPE-RES-32K
    11. 9544
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to fluid dynamics and flow control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MERCHANTABILITY
    -0.23
    (configuration
    -0.23
     recommendations
    -0.23
     correspondence
    -0.23
     instrumentation
    -0.22
     telecommunications
    -0.22
    .configuration
    -0.22
     characterization
    -0.22
     Recommendations
    -0.22
     accommodations
    -0.21
    POSITIVE LOGITS
     &↵
    0.14
    ↵
    0.13
     WithEvents
    0.13
    onavir
    0.12
     wholly
    0.12
    myModal
    0.12
     topics
    0.12
     aspects
    0.12
     пÑĢакÑĤи
    0.12
     purely
    0.12
    Activations Density 0.155%

    No Known Activations