© 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. 15642
    Prev
    Next
    INDEX
    Explanations

    phrases related to official documents and reporting

    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
     Glo
    -0.17
     Antworten
    -0.17
    uther
    -0.16
    ve
    -0.16
    ligt
    -0.16
     Yön
    -0.15
     glo
    -0.15
    acre
    -0.15
    imli
    -0.15
     Witness
    -0.15
    POSITIVE LOGITS
    #ab
    0.21
    punk
    0.18
    ìĿ´ë¹Ħ
    0.18
    rada
    0.17
    ung
    0.16
    ende
    0.16
    ungs
    0.16
    imson
    0.16
    eza
    0.15
    isan
    0.15
    Activations Density 0.053%

    No Known Activations