© 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 EvalsExportsinterp-engineNEWAPI 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. 44212
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing simplicity and ease of use

    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
    pires
    -0.17
    ãĥĮ
    -0.16
    .lu
    -0.15
    akis
    -0.15
    eyJ
    -0.14
     Wanted
    -0.14
    ients
    -0.14
    ecko
    -0.14
    wanted
    -0.14
    adeon
    -0.13
    POSITIVE LOGITS
     need
    0.44
    need
    0.36
     needs
    0.33
     Need
    0.31
    Need
    0.29
    éľĢ
    0.28
    éľĢè¦ģ
    0.27
    needs
    0.27
     needing
    0.24
     besoin
    0.24
    Activations Density 0.027%

    No Known Activations