© 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. 22910
    Prev
    Next
    INDEX
    Explanations

    prepositions and related phrases indicating connections or relationships

    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
     Ihre
    -0.16
     Your
    -0.15
    Your
    -0.15
     their
    -0.15
     Their
    -0.15
     your
    -0.14
    èĢħçļĦ
    -0.14
    uler
    -0.13
     thy
    -0.13
    ¢
    -0.13
    POSITIVE LOGITS
     us
    0.70
     him
    0.68
     me
    0.57
     them
    0.53
     lui
    0.47
    him
    0.43
    them
    0.43
     ihn
    0.42
     ihm
    0.41
     емÑĥ
    0.35
    Activations Density 0.007%

    No Known Activations