© 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. 8570
    Prev
    Next
    INDEX
    Explanations

    phrases about equality and discrimination in societal contexts

    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
    TRS
    -0.15
    ắng
    -0.14
    avage
    -0.13
    звиÑĩай
    -0.13
    анка
    -0.13
    overe
    -0.12
    ë´ī
    -0.12
    .tpl
    -0.12
     tempt
    -0.12
     Hans
    -0.12
    POSITIVE LOGITS
     discrimination
    0.49
     discriminate
    0.47
     discrim
    0.46
     Discrim
    0.46
     discrimin
    0.42
     discriminator
    0.38
     discriminatory
    0.36
     differentiation
    0.34
    iscrimination
    0.31
     distinction
    0.31
    Activations Density 0.047%

    No Known Activations