© 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. 28728
    Prev
    Next
    INDEX
    Explanations

    references to accusations and legal defenses

    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
     were
    -0.27
     weren
    -0.25
     Were
    -0.21
    were
    -0.21
    Were
    -0.20
     fueron
    -0.19
     wurden
    -0.18
     باشÙĨد
    -0.16
    eren
    -0.16
     είÏĩαν
    -0.16
    POSITIVE LOGITS
     دارد
    0.19
     íķľëĭ¤
    0.19
    ¤ëĭ¤
    0.18
     tiene
    0.18
     is
    0.18
    uje
    0.17
     रà¤ĸत
    0.17
    ÑĭваеÑĤ
    0.17
     ÎŃÏĩει
    0.17
    ãģ¦ãģĦãĤĭ
    0.17
    Activations Density 0.018%

    No Known Activations