© 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. 17246
    Prev
    Next
    INDEX
    Explanations

    moments of reflection and mindfulness

    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
    ixin
    -0.13
    说è¯Ŀ
    -0.13
     Å¡p
    -0.12
     spolup
    -0.12
    大åĪ©
    -0.12
    éħįåIJĪ
    -0.12
    TestMethod
    -0.12
    رز
    -0.12
    VERTISE
    -0.11
    OperationException
    -0.11
    POSITIVE LOGITS
     reflect
    0.54
     reflection
    0.53
     Reflect
    0.48
     reflecting
    0.47
    reflect
    0.47
    Reflect
    0.47
     reflective
    0.44
    reflection
    0.44
     Reflection
    0.42
     reflections
    0.42
    Activations Density 0.406%

    No Known Activations