Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 41542
    Prev
    Next
    INDEX
    Explanations

    significant milestones or impactful developments in various contexts

    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
     interesting
    -0.18
    Äĥ
    -0.15
     usual
    -0.15
    803
    -0.14
     onCancelled
    -0.14
     important
    -0.14
     useful
    -0.14
    coop
    -0.13
    good
    -0.13
     popular
    -0.13
    POSITIVE LOGITS
     truly
    0.26
     ver
    0.21
     Truly
    0.19
     absolutely
    0.18
     completely
    0.16
     true
    0.16
     Completely
    0.16
     Absolutely
    0.15
    羣æŃ£
    0.15
     complete
    0.14
    Activations Density 0.127%

    No Known Activations