© 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. 30439
    Prev
    Next
    INDEX
    Explanations

    the phrase "is" in various contexts

    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
    ÅĽmy
    -0.16
    ex
    -0.14
     previously
    -0.14
    itecture
    -0.14
    trap
    -0.14
     -*-č↵
    -0.14
    ORMAL
    -0.14
    ctrine
    -0.13
    ymoon
    -0.13
    ansom
    -0.13
    POSITIVE LOGITS
    ometric
    0.24
    rael
    0.23
    otope
    0.22
     hereby
    0.21
    omorphic
    0.20
    othermal
    0.20
    omer
    0.19
    /w
    0.18
    csi
    0.18
    lam
    0.18
    Activations Density 0.036%

    No Known Activations