© 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. 22673
    Prev
    Next
    INDEX
    Explanations

    monetary values and numerical data related to prizes or costs

    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
    ruž
    -0.16
    alu
    -0.14
    Ь
    -0.14
    ring
    -0.14
    -exc
    -0.14
    weise
    -0.13
     istem
    -0.13
    aż
    -0.13
    -0.13
    atron
    -0.13
    POSITIVE LOGITS
    0
    0.39
    ï¼IJ
    0.22
    00
    0.21
    9
    0.18
    5
    0.18
    8
    0.17
    Û°
    0.16
    6
    0.16
    7
    0.16
    åķ
    0.16
    Activations Density 0.027%

    No Known Activations