© 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. 12474
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disappointment and self-preservation

    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
     Damon
    -0.23
    Delegate
    -0.17
     Damascus
    -0.16
     Dil
    -0.15
     Delegate
    -0.14
     Digest
    -0.14
    adian
    -0.14
     DataTable
    -0.14
    roz
    -0.14
    Dict
    -0.13
    POSITIVE LOGITS
     dry
    1.13
     Dry
    1.00
    dry
    0.96
    Dry
    0.93
     drying
    0.86
     dried
    0.82
     dryer
    0.76
     khô
    0.66
    ä¹¾
    0.62
     ÑģÑĥÑħ
    0.61
    Activations Density 0.036%

    No Known Activations