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

    Neuronpedia

    Jacobian LensNEW
    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. 42974
    Prev
    Next
    INDEX
    Explanations

    mathematical equalities and comparisons

    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
    ãģªãģĦ
    -0.18
    ================
    -0.18
    "
    -0.16
    ======↵
    -0.16
    (
    -0.16
    ↵
    -0.15
    Ùĩ
    -0.15
    á»ħ
    -0.15
    mey
    -0.15
    ====↵
    -0.14
    POSITIVE LOGITS
    /=
    0.37
    *=*=
    0.22
    /is
    0.17
    ==============
    0.16
    âĩ
    0.16
    âķĿ
    0.16
    ========
    0.16
    SGlobal
    0.15
    /-
    0.15
    ===============
    0.15
    Activations Density 0.054%

    No Known Activations