© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 25498
    Prev
    Next
    INDEX
    Explanations

    discussions about the complexities of relationships and societal perceptions of bisexuality

    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
    íĨłíĨł
    -0.16
    jvu
    -0.15
     actionTypes
    -0.15
    herited
    -0.14
     moto
    -0.14
    âĸį
    -0.14
    SpaceItem
    -0.14
    (åľŁ
    -0.14
     Mev
    -0.14
    eyen
    -0.13
    POSITIVE LOGITS
     relationships
    0.32
     couples
    0.29
     couple
    0.28
     romantic
    0.28
     marriage
    0.28
     relationship
    0.27
     unions
    0.26
     partnerships
    0.25
     mon
    0.25
     Relationships
    0.24
    Activations Density 0.097%

    No Known Activations