© 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. 12498
    Prev
    Next
    INDEX
    Explanations

    concepts related to identity transformation and memory retention

    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
     haven
    -0.23
     hadn
    -0.23
     had
    -0.21
     Äijã
    -0.20
     à¤īसन
    -0.20
     telah
    -0.19
    ’ve
    -0.19
     weren
    -0.18
     waren
    -0.17
    ãģĮãģĤãģ£ãģŁ
    -0.17
    POSITIVE LOGITS
     becomes
    0.51
     become
    0.36
     gets
    0.34
     wird
    0.34
     wordt
    0.33
     blir
    0.32
     comes
    0.30
     will
    0.30
     begins
    0.29
    bec
    0.29
    Activations Density 0.219%

    No Known Activations