© 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. 23896
    Prev
    Next
    INDEX
    Explanations

    terms related to effectiveness and severity in various contexts, particularly focusing on outcomes

    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
     Throughout
    -0.17
     even
    -0.17
    even
    -0.15
     throughout
    -0.14
     Even
    -0.14
    Even
    -0.14
    Throughout
    -0.14
    opal
    -0.14
    raman
    -0.13
    åĪ°åºķ
    -0.13
    POSITIVE LOGITS
     when
    0.50
     if
    0.40
    when
    0.38
     cuando
    0.36
     wenn
    0.36
     quando
    0.35
     whenever
    0.34
     lorsque
    0.34
    	when
    0.31
     jika
    0.31
    Activations Density 0.103%

    No Known Activations