© 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. 22889
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with legal and societal issues

    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
     thereby
    -0.16
    à¸ĩà¸Ńย
    -0.15
    ï¼ĮåIJĮæŶ
    -0.14
    ORY
    -0.13
    Whats
    -0.13
    ÐĶÐļ
    -0.13
    æĺ¯ä»Ģä¹Ī
    -0.13
    ãģĭãģĦ
    -0.13
    rix
    -0.12
    ãģĿãģĹãģ¦
    -0.12
    POSITIVE LOGITS
     where
    0.96
    where
    0.74
     où
    0.63
     donde
    0.62
     Where
    0.62
    	where
    0.61
    Where
    0.58
    _where
    0.58
     ÏĮÏĢοÏħ
    0.57
     где
    0.57
    Activations Density 0.094%

    No Known Activations