© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 22853
    Prev
    Next
    INDEX
    Explanations

    discussions related to costs and issues surrounding various topics

    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
    ãĥ³ãĤ¯
    -0.14
    rof
    -0.13
    MatrixMode
    -0.13
    uter
    -0.13
    eras
    -0.13
    jen
    -0.12
     инÑĦоÑĢма
    -0.12
    ÐĦ
    -0.12
    kus
    -0.12
    readcr
    -0.12
    POSITIVE LOGITS
     fate
    0.32
     nature
    0.29
     merits
    0.29
     meaning
    0.28
     appropri
    0.28
     advis
    0.28
     whether
    0.28
     possibility
    0.28
    æĺ¯åIJ¦
    0.27
     status
    0.26
    Activations Density 0.183%

    No Known Activations