© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 43751
    Prev
    Next
    INDEX
    Explanations

    descriptive language related to visuals and sensory experiences

    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
    ové
    -0.14
    Ľi
    -0.13
     proport
    -0.13
    wiÄħ
    -0.13
    rega
    -0.13
    ÑĢе
    -0.13
    wj
    -0.12
     rather
    -0.12
     somewhat
    -0.12
    ......
    -0.12
    POSITIVE LOGITS
    женÑĮ
    0.14
    Ĩ
    0.13
     dissolve
    0.13
     secretive
    0.12
    ãģ¾ãģ¾
    0.12
     неÑİ
    0.12
    ãĥģãĥ¥
    0.12
     Substance
    0.12
     POSSIBILITY
    0.11
    -pills
    0.11
    Activations Density 0.153%

    No Known Activations