© 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. 28573
    Prev
    Next
    INDEX
    Explanations

    expressions of commitment and continuity

    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
    olith
    -0.17
    大人
    -0.16
    omorphic
    -0.14
    ród
    -0.14
    اÙĥÙħ
    -0.14
    ico
    -0.14
    RG
    -0.14
    nout
    -0.13
    ÑĢаÑĩ
    -0.13
    าà¸ģร
    -0.13
    POSITIVE LOGITS
     forever
    0.48
     Forever
    0.39
     will
    0.37
    Forever
    0.36
    æ°¸
    0.33
     always
    0.33
    will
    0.31
     et
    0.30
     Always
    0.30
     FORE
    0.29
    Activations Density 0.027%

    No Known Activations