© 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. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 22713
    Prev
    Next
    INDEX
    Explanations

    references to climate change and its impacts on ice sheets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Juliushanhanhan/llama-3-8b-it-res/blocks.25.hook_resid_post
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    gated
    Context Size
    1,024
    Dataset
    Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mov
    -0.15
     distortion
    -0.15
     distorted
    -0.14
    .pt
    -0.14
     veteran
    -0.13
    /render
    -0.13
     borderline
    -0.13
     Hunger
    -0.13
    fung
    -0.13
     κά
    -0.13
    POSITIVE LOGITS
     diagnosed
    0.20
     ensemble
    0.20
     IPCC
    0.19
     Ensemble
    0.19
     adv
    0.19
     clim
    0.18
    forcing
    0.18
     EOF
    0.18
    ensemble
    0.18
     aeros
    0.17
    Activations Density 0.027%

    No Known Activations