© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 42282
    Prev
    Next
    INDEX
    Explanations

    references to films and filmmaking, particularly in relation to directors and their works

    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
     versions
    -0.16
    eph
    -0.15
     Episodes
    -0.15
    ê¶ģ
    -0.15
    uvw
    -0.15
    isodes
    -0.14
     GiỼi
    -0.14
    æ¡IJ
    -0.14
    ibur
    -0.14
    ÅĽmy
    -0.14
    POSITIVE LOGITS
     feature
    0.34
     studio
    0.27
     Feature
    0.26
    feature
    0.25
    Feature
    0.25
     solo
    0.25
    -feature
    0.23
     FEATURE
    0.22
    _feature
    0.21
    (feature
    0.21
    Activations Density 0.035%

    No Known Activations