© 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. 8755
    Prev
    Next
    INDEX
    Explanations

    references to American organizations related to politics or influence

    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
    interop
    -0.17
    ipeg
    -0.17
    iah
    -0.16
    heim
    -0.15
    464
    -0.15
    ietf
    -0.14
    avic
    -0.14
    375
    -0.14
    åľ³
    -0.14
     laure
    -0.14
    POSITIVE LOGITS
     Samoa
    0.19
    os
    0.16
    esi
    0.16
     Enterprise
    0.15
    values
    0.15
    etxt
    0.15
     VALUES
    0.14
    ä¿Ŀ
    0.14
     values
    0.14
     Values
    0.14
    Activations Density 0.011%

    No Known Activations