© 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. 42196
    Prev
    Next
    INDEX
    Explanations

    references to "last" in varying contexts, suggesting a focus on films or narratives about endings or finality

    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
     latest
    -0.17
    lets
    -0.16
    _latest
    -0.16
    виÑĩ
    -0.15
    istar
    -0.15
    liÄŁinin
    -0.15
    latest
    -0.14
    ohl
    -0.14
    prox
    -0.14
     eget
    -0.14
    POSITIVE LOGITS
     remaining
    0.31
     straw
    0.30
    est
    0.28
    remaining
    0.27
     hur
    0.26
     vest
    0.26
     bast
    0.25
    Remaining
    0.25
     Remaining
    0.24
    -minute
    0.24
    Activations Density 0.033%

    No Known Activations