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. 29877
    Prev
    Next
    INDEX
    Explanations

    mentions of ongoing actions or processes involving notable figures

    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
     recently
    -0.36
     recent
    -0.35
    recent
    -0.31
     soon
    -0.31
     currently
    -0.27
    soon
    -0.26
     Recently
    -0.24
     presently
    -0.24
     lately
    -0.24
    currently
    -0.23
    POSITIVE LOGITS
     repeatedly
    0.20
     altern
    0.20
     gradually
    0.20
     twice
    0.20
     increasingly
    0.18
     steadily
    0.18
     slowly
    0.17
     whenever
    0.17
    avaÅŁ
    0.17
     watched
    0.17
    Activations Density 0.086%

    No Known Activations