© 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. 33584
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or intentions related to social activism

    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
    å¸Ń
    -0.16
    egis
    -0.14
    ENCH
    -0.14
     Offensive
    -0.14
    .lex
    -0.14
    PickerController
    -0.14
    IFI
    -0.14
    bench
    -0.14
    _tA
    -0.14
    odnÃŃ
    -0.14
    POSITIVE LOGITS
     voice
    0.34
     express
    0.33
     protest
    0.27
     expression
    0.27
     vo
    0.27
    express
    0.27
     voices
    0.26
    Express
    0.26
     expresses
    0.26
     vent
    0.26
    Activations Density 0.070%

    No Known Activations