© 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 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. 43302
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "it," particularly as a subject or topic in discussions of social 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
    ÑģÑĤÑİ
    -0.15
    Ø´ÙĪ
    -0.14
    [section
    -0.14
    .strict
    -0.13
    uja
    -0.13
    å¡ŀ
    -0.13
    andon
    -0.13
    hm
    -0.13
    amp
    -0.13
    é¬
    -0.12
    POSITIVE LOGITS
     is
    0.27
     beh
    0.24
     takes
    0.22
     matter
    0.20
     would
    0.19
     taking
    0.18
     take
    0.17
    iner
    0.17
     important
    0.17
    ching
    0.17
    Activations Density 0.166%

    No Known Activations