© 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. 42331
    Prev
    Next
    INDEX
    Explanations

    phrases related to hypothetical situations involving groups of people and violent acts

    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
     somewhat
    -0.24
     usually
    -0.17
     rather
    -0.17
     unless
    -0.16
     mostly
    -0.15
    mostly
    -0.15
    usually
    -0.14
    æľīçĤ¹
    -0.14
     slightly
    -0.14
    rellas
    -0.14
    POSITIVE LOGITS
     entirely
    0.29
     completely
    0.27
     simply
    0.27
     perfectly
    0.27
     anytime
    0.27
     anything
    0.24
     any
    0.23
     Completely
    0.22
     anywhere
    0.22
     ANY
    0.22
    Activations Density 0.032%

    No Known Activations