© 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. 28633
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievements or milestones in a context where something reaches its peak or highest point

    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
    ãĥ¼ãĥijãĥ¼
    -0.15
    ongo
    -0.14
    assa
    -0.14
    ivil
    -0.14
    .Gradient
    -0.14
    evin
    -0.14
    olia
    -0.13
    appa
    -0.13
    iola
    -0.13
    uiltin
    -0.13
    POSITIVE LOGITS
     high
    0.82
    high
    0.68
     low
    0.68
     High
    0.66
    High
    0.63
    -high
    0.61
    low
    0.58
     HIGH
    0.57
    é«ĺ
    0.56
    _high
    0.54
    Activations Density 0.020%

    No Known Activations