© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41746
    Prev
    Next
    INDEX
    Explanations

    phrases related to recent developments or updates

    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
     latest
    -0.18
     recently
    -0.18
     currently
    -0.16
    ombo
    -0.15
     Latest
    -0.15
     previously
    -0.15
     Recently
    -0.14
    thing
    -0.14
    ardi
    -0.14
    Recently
    -0.13
    POSITIVE LOGITS
    /current
    0.28
     developments
    0.24
    emente
    0.23
     trends
    0.23
    ral
    0.22
    ;y
    0.21
     Develop
    0.19
     advances
    0.19
    ily
    0.18
    mente
    0.17
    Activations Density 0.034%

    No Known Activations