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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54735
    Prev
    Next
    INDEX
    Explanations

    concepts related to the reversal of events and processes over time

    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
    à¥Ģण
    -0.16
    urope
    -0.14
    zier
    -0.14
    dej
    -0.14
    amarin
    -0.13
     Renew
    -0.13
     Rena
    -0.13
    avar
    -0.13
     sát
    -0.13
    porto
    -0.13
    POSITIVE LOGITS
     reverse
    1.09
     reversed
    1.04
     Reverse
    1.00
     reversal
    0.96
    reverse
    0.94
    Reverse
    0.92
     reversing
    0.91
     revers
    0.88
    .reverse
    0.79
    _reverse
    0.77
    Activations Density 0.025%

    No Known Activations