© 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. 41297
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing the concept of "best" in various contexts

    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
    odule
    -0.16
    963
    -0.16
     Matters
    -0.15
    )const
    -0.14
    agonal
    -0.14
    ÑĨеп
    -0.13
    emes
    -0.13
    agua
    -0.13
    erable
    -0.13
    оло
    -0.13
    POSITIVE LOGITS
     way
    0.47
     thing
    0.36
     Way
    0.28
    way
    0.28
     WAY
    0.28
    .way
    0.27
    thing
    0.27
     course
    0.25
    -way
    0.24
    _way
    0.23
    Activations Density 0.048%

    No Known Activations