© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 30415
    Prev
    Next
    INDEX
    Explanations

    details regarding the launch sequence and technical specifications of rockets

    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
    Transmission
    -0.16
    weathermap
    -0.15
     maduras
    -0.15
     seiz
    -0.14
     Avalanche
    -0.14
     Bilder
    -0.14
    .Transport
    -0.14
    bé
    -0.13
     FetchType
    -0.13
    бом
    -0.13
    POSITIVE LOGITS
     thrust
    0.35
     Thr
    0.32
     engines
    0.32
     Engines
    0.31
     thr
    0.30
     prop
    0.28
     engine
    0.27
     burn
    0.27
    æİ¨
    0.26
    thr
    0.25
    Activations Density 0.032%

    No Known Activations