© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 54079
    Prev
    Next
    INDEX
    Explanations

    topics related to public safety incidents or serious events

    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
    allas
    -0.16
    .Designer
    -0.13
    ζα
    -0.13
     slaughtered
    -0.13
     Assass
    -0.13
    astic
    -0.12
    .dateFormat
    -0.12
    aye
    -0.12
     scandals
    -0.12
    æĪĺäºī
    -0.12
    POSITIVE LOGITS
     police
    0.16
     victim
    0.16
     Odin
    0.16
     vaz
    0.14
    ONTAL
    0.13
     report
    0.13
    victim
    0.12
    ÏĨο
    0.12
    #Region
    0.12
     Vital
    0.12
    Activations Density 0.025%

    No Known Activations