© 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. 41859
    Prev
    Next
    INDEX
    Explanations

    references to reports or studies involving space industry initiatives

    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
    itespace
    -0.14
    wcs
    -0.13
    ãģŁãģĹ
    -0.12
    UIColor
    -0.12
     Forums
    -0.12
    صاÙĦ
    -0.12
    MLE
    -0.12
    azzo
    -0.11
    izz
    -0.11
     Boo
    -0.11
    POSITIVE LOGITS
    EG
    0.49
     EG
    0.47
     SG
    0.45
    IG
    0.45
     IG
    0.45
    SG
    0.43
     AG
    0.43
     LG
    0.42
     RG
    0.42
     PG
    0.41
    Activations Density 0.011%

    No Known Activations