© 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. 25906
    Prev
    Next
    INDEX
    Explanations

    terms related to food and dietary concepts

    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
    ITU
    -0.19
    -unstyled
    -0.17
    uestion
    -0.16
    ENCIL
    -0.16
    anson
    -0.16
    orre
    -0.16
    ustin
    -0.16
    cape
    -0.16
    abay
    -0.15
    лиÑĩ
    -0.15
    POSITIVE LOGITS
    ary
    0.56
    naire
    0.51
    ally
    0.48
    ality
    0.45
    naires
    0.45
    ed
    0.41
    als
    0.41
    aries
    0.41
    er
    0.40
    nement
    0.38
    Activations Density 0.031%

    No Known Activations