© 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. 55062
    Prev
    Next
    INDEX
    Explanations

    phrases indicating subjective experiences and emotional reactions

    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
    @qq
    -0.14
    )prepare
    -0.14
    indsight
    -0.14
    PRETTY
    -0.14
    actionDate
    -0.14
    åķ
    -0.13
    ller
    -0.13
     facil
    -0.13
    owell
    -0.13
     whence
    -0.13
    POSITIVE LOGITS
     finally
    0.77
    finally
    0.66
     Finally
    0.61
    Finally
    0.56
    ç»Īäºİ
    0.44
     FIN
    0.40
    	finally
    0.38
     suddenly
    0.38
    Lastly
    0.34
     Lastly
    0.33
    Activations Density 0.012%

    No Known Activations