Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23769
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluation and criticism

    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
    uti
    -0.16
    à¸ŀà¸Ń
    -0.15
    ronic
    -0.15
    ếp
    -0.15
    μβ
    -0.14
     Beste
    -0.14
    apolis
    -0.14
    uter
    -0.13
    bane
    -0.13
    ryan
    -0.13
    POSITIVE LOGITS
     without
    0.37
    without
    0.35
     arbitrary
    0.32
     Without
    0.32
     random
    0.30
     WITHOUT
    0.29
    Without
    0.29
     randomly
    0.28
     ohne
    0.28
     Arbitrary
    0.28
    Activations Density 0.061%

    No Known Activations