© 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. 15584
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to geology and environmental effects

    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
     Tiny
    -0.16
    -0.15
     normal
    -0.15
     study
    -0.15
     known
    -0.14
     using
    -0.14
    Tiny
    -0.14
     AS
    -0.14
     varying
    -0.14
     orderly
    -0.14
    POSITIVE LOGITS
    ynchronously
    0.16
     eldre
    0.16
    Å¡ek
    0.16
     adv
    0.15
    #ac
    0.14
    oÄŁ
    0.14
     Contemporary
    0.14
     дог
    0.14
    ůvod
    0.14
     Contribution
    0.13
    Activations Density 0.029%

    No Known Activations