© 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. 24-LLAMASCOPE-RES-32K
    11. 18416
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental sustainability and green initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Appalachian
    -0.18
     Newfoundland
    -0.16
     Bras
    -0.15
     tornado
    -0.15
     Charlottesville
    -0.15
     Louisville
    -0.15
     Appalach
    -0.15
     atl
    -0.15
    Monad
    -0.14
    Philadelphia
    -0.14
    POSITIVE LOGITS
     California
    0.71
     Californ
    0.66
     Los
    0.65
    California
    0.64
    Los
    0.58
     california
    0.56
     Sacramento
    0.55
     Calif
    0.54
     UCLA
    0.52
     LA
    0.48
    Activations Density 1.311%

    No Known Activations