© 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. 41321
    Prev
    Next
    INDEX
    Explanations

    terms related to game mechanics and updates

    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
    odesk
    -0.14
     Js
    -0.14
     orig
    -0.13
     treff
    -0.13
    arness
    -0.13
    untu
    -0.13
    æī£
    -0.13
    okit
    -0.13
    ãĥ³ãĥIJ
    -0.12
    æ£ļ
    -0.12
    POSITIVE LOGITS
     patch
    0.26
     Patch
    0.23
    patch
    0.22
    Patch
    0.22
    .gg
    0.20
     PTR
    0.20
     PATCH
    0.19
     community
    0.19
     Community
    0.19
    Community
    0.18
    Activations Density 0.164%

    No Known Activations