© 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. 24294
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods or months

    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
    atch
    -0.17
    elman
    -0.15
    pis
    -0.15
    longleftrightarrow
    -0.15
    ult
    -0.15
    headed
    -0.14
    nis
    -0.14
    cce
    -0.14
    ãĥĥãĤ°
    -0.14
    ourg
    -0.14
    POSITIVE LOGITS
    /year
    0.32
    -long
    0.28
    份
    0.28
     Madness
    0.26
    gomery
    0.22
    lies
    0.21
    iversary
    0.21
    éĸĵ
    0.21
    andise
    0.19
    engers
    0.19
    Activations Density 0.050%

    No Known Activations