© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 24469
    Prev
    Next
    INDEX
    Explanations

    instances of apologies and expressions of remorse

    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
    aln
    -0.15
    ÎŃÏģγ
    -0.15
    staking
    -0.14
     öden
    -0.14
     kabil
    -0.14
     erotik
    -0.14
    ADX
    -0.14
    _hz
    -0.14
     mặc
    -0.14
    Statics
    -0.14
    POSITIVE LOGITS
     prof
    0.30
     for
    0.29
    prof
    0.21
     again
    0.20
     twice
    0.19
    for
    0.19
    again
    0.18
    	for
    0.17
     Prof
    0.17
    Prof
    0.16
    Activations Density 0.030%

    No Known Activations