© 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 EvalsExportsAPI 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. 23770
    Prev
    Next
    INDEX
    Explanations

    multiple occurrences of definite articles and pronouns, indicating a focus on highlighting specific subjects or themes in the text

    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
    ÏĦικα
    -0.14
    alog
    -0.14
     behalf
    -0.14
    rosis
    -0.14
    .Expressions
    -0.14
    ENCIL
    -0.14
     Month
    -0.14
    rapy
    -0.13
    zero
    -0.13
    ινÏīν
    -0.13
    POSITIVE LOGITS
     situation
    0.26
     scene
    0.23
     Situation
    0.23
     sound
    0.21
     crowd
    0.21
     sounds
    0.20
     atmosphere
    0.20
     mood
    0.18
    ULK
    0.17
    åľº
    0.17
    Activations Density 0.068%

    No Known Activations