© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 30208
    Prev
    Next
    INDEX
    Explanations

    references to technology and product features, particularly related to gadgets and tools

    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
    æķij
    -0.15
    Ïģια
    -0.15
    oeff
    -0.14
    åIJIJ
    -0.14
     Sustainability
    -0.14
    UTTON
    -0.13
    _decimal
    -0.13
    .gs
    -0.13
    esar
    -0.13
    zar
    -0.13
    POSITIVE LOGITS
     holder
    0.38
     case
    0.35
     holders
    0.34
     Holder
    0.31
     cases
    0.31
    holder
    0.29
     Cases
    0.29
     hol
    0.28
    -holder
    0.28
    -case
    0.28
    Activations Density 0.021%

    No Known Activations