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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29192
    Prev
    Next
    INDEX
    Explanations

    statistical comparisons or changes in data over time

    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
    amina
    -0.14
    ạ
    -0.14
     Pazar
    -0.13
    tics
    -0.13
     wÅĤa
    -0.13
    à¹Ģสร
    -0.13
    eteria
    -0.12
    ancock
    -0.12
    \Php
    -0.12
    mtx
    -0.12
    POSITIVE LOGITS
     last
    0.37
     previous
    0.33
    last
    0.28
    previous
    0.27
     earlier
    0.25
     levels
    0.25
    -last
    0.23
     pre
    0.23
     what
    0.22
     past
    0.22
    Activations Density 0.110%

    No Known Activations