© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 24486
    Prev
    Next
    INDEX
    Explanations

    expressions related to potential and development

    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
    reon
    -0.17
    addy
    -0.14
    alon
    -0.14
    dag
    -0.14
    amel
    -0.13
     accompl
    -0.13
     acquiring
    -0.13
     ease
    -0.13
     Pall
    -0.12
    ystone
    -0.12
    POSITIVE LOGITS
     tap
    0.50
     harness
    0.49
     tapping
    0.46
     Tap
    0.46
     tapped
    0.45
    Tap
    0.45
     exploitation
    0.43
     Harness
    0.42
    Harness
    0.42
     taps
    0.42
    Activations Density 0.050%

    No Known Activations