© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 21165
    Prev
    Next
    INDEX
    Explanations

    technical terms and acronyms related to computing and software architectures

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     (
    -0.26
     ("
    -0.25
     (“
    -0.22
     ($
    -0.20
     ('
    -0.18
     (**
    -0.18
    .").
    -0.17
     (#
    -0.17
     (\
    -0.17
    !↵↵↵↵↵↵
    -0.17
    POSITIVE LOGITS
    )
    0.39
    ),
    0.29
    ):
    0.26
    )↵
    0.24
    );
    0.22
    ):↵
    0.21
    )]
    0.19
    )ØĮ
    0.19
    ),↵
    0.19
    );↵
    0.18
    Activations Density 0.697%

    No Known Activations