© 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. 63228
    Prev
    Next
    INDEX
    Explanations

    references to collaborative projects and team dynamics

    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
    aket
    -0.16
    ench
    -0.15
     Simply
    -0.14
    *
    -0.14
    lew
    -0.14
    æѤ
    -0.14
    ere
    -0.13
     thang
    -0.13
    istine
    -0.13
    ebin
    -0.13
    POSITIVE LOGITS
     like
    0.38
     probably
    0.34
     maybe
    0.33
    like
    0.28
    probably
    0.27
    maybe
    0.26
     around
    0.26
     Probably
    0.25
     Like
    0.25
     anywhere
    0.25
    Activations Density 0.155%

    No Known Activations