© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 25532
    Prev
    Next
    INDEX
    Explanations

    references to social injustices and discrimination experienced by marginalized communities

    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
    ADER
    -0.16
    çĬ¯
    -0.15
    afil
    -0.15
    ught
    -0.15
     chute
    -0.15
    ÑĹ
    -0.14
     sodom
    -0.14
    .addObserver
    -0.14
    ooke
    -0.14
    .Side
    -0.14
    POSITIVE LOGITS
     discrimination
    0.40
     Discrim
    0.32
     discrim
    0.28
     discrimin
    0.25
     discriminatory
    0.25
     discriminate
    0.24
     harassment
    0.23
    iscrimination
    0.23
     barriers
    0.21
    disc
    0.21
    Activations Density 0.116%

    No Known Activations