© 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. 33577
    Prev
    Next
    INDEX
    Explanations

    articles and auxiliary verbs indicating existence or quality

    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
    hle
    -0.17
    .ie
    -0.15
    åĤ
    -0.14
    ubbo
    -0.14
    thora
    -0.13
     Purpose
    -0.13
    ews
    -0.13
    _PIX
    -0.13
    yster
    -0.12
    esian
    -0.12
    POSITIVE LOGITS
     problem
    0.30
     concern
    0.28
     challenge
    0.27
     liability
    0.23
     issue
    0.22
    problem
    0.22
     factor
    0.21
     source
    0.21
     major
    0.21
     hind
    0.21
    Activations Density 0.151%

    No Known Activations