© 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. 43575
    Prev
    Next
    INDEX
    Explanations

    numerical data related to statistics or reports

    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
     Dil
    -0.17
     dil
    -0.15
    okies
    -0.15
     Dion
    -0.14
     Doll
    -0.14
    istle
    -0.14
    obili
    -0.14
    dj
    -0.14
    .simps
    -0.14
    dol
    -0.13
    POSITIVE LOGITS
    20
    0.70
     twentieth
    0.48
    Û²Û°
    0.45
     download
    0.42
    020
    0.41
    २०
    0.36
     twenty
    0.36
    ï¼Ĵï¼IJ
    0.35
    äºĮåįģ
    0.34
     двад
    0.34
    Activations Density 0.011%

    No Known Activations