© 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. 55421
    Prev
    Next
    INDEX
    Explanations

    references to brass as a material or instrument

    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
     Dodd
    -0.16
    isms
    -0.16
    огÑĥ
    -0.15
    aths
    -0.15
     absor
    -0.15
    μοÏħ
    -0.15
    ipur
    -0.15
    оналÑĮ
    -0.15
    ansa
    -0.15
    afil
    -0.15
    POSITIVE LOGITS
    erie
    0.23
    iere
    0.22
    ieres
    0.22
    icas
    0.20
    ica
    0.20
    ilia
    0.18
    ière
    0.17
    nika
    0.17
    s
    0.16
    nuts
    0.16
    Activations Density 0.003%

    No Known Activations