© 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. 54171
    Prev
    Next
    INDEX
    Explanations

    monetary values or financial amounts

    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
    98
    -0.16
    95
    -0.15
    çĻ¾
    -0.14
     hundred
    -0.14
    100
    -0.14
    £½
    -0.14
    97
    -0.14
     Hundred
    -0.13
    _RST
    -0.13
    ÛµÛ°
    -0.13
    POSITIVE LOGITS
    26
    0.55
    29
    0.54
    28
    0.54
    27
    0.53
    25
    0.49
    24
    0.47
    23
    0.44
    22
    0.42
     twenty
    0.41
    30
    0.39
    Activations Density 0.064%

    No Known Activations