© 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. 26191
    Prev
    Next
    INDEX
    Explanations

    phrases associated with evaluation and critique, particularly in relation to films and societal issues

    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
     And
    -0.21
    1
    -0.20
    And
    -0.19
     But
    -0.19
    2
    -0.19
    0
    -0.17
     à¹ģละ
    -0.17
    But
    -0.17
     Or
    -0.16
    3
    -0.15
    POSITIVE LOGITS
    ;
    0.38
    ;if
    0.26
    ï¼Ľ
    0.25
    ØĽ
    0.25
    __;
    0.24
    _;
    0.23
    %;
    0.23
    ;$
    0.21
    ;r
    0.21
    ;.
    0.21
    Activations Density 0.167%

    No Known Activations