© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 40647
    Prev
    Next
    INDEX
    Explanations

    references to specific needs and requirements

    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
     needed
    -0.21
    Needed
    -0.19
     Needed
    -0.19
    _needed
    -0.17
    ergic
    -0.16
    needed
    -0.16
    -needed
    -0.16
    uzzi
    -0.16
    ettle
    -0.15
    isson
    -0.15
    POSITIVE LOGITS
    lessly
    0.29
    iest
    0.22
    /w
    0.21
     met
    0.20
    /request
    0.20
    iness
    0.19
    /preferences
    0.17
    dle
    0.16
     satisfaction
    0.15
    ps
    0.15
    Activations Density 0.018%

    No Known Activations