© 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. 42117
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical data or code

    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
    ernel
    -0.15
    c
    -0.14
    s
    -0.14
    ero
    -0.14
    yn
    -0.14
    ron
    -0.14
    i
    -0.14
     Bian
    -0.13
    arra
    -0.13
     I
    -0.13
    POSITIVE LOGITS
    _RCC
    0.20
    ñana
    0.17
    VisualStyle
    0.15
    _tD
    0.15
    .metamodel
    0.15
     ActionTypes
    0.15
    μιÏĥ
    0.15
     rám
    0.15
    ForMember
    0.14
    storybook
    0.14
    Activations Density 0.015%

    No Known Activations