© 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. 42325
    Prev
    Next
    INDEX
    Explanations

    phrases related to improvement and progress 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
     tougher
    -0.14
    ISIBLE
    -0.13
    tier
    -0.13
    γοÏħ
    -0.13
    blind
    -0.13
    asco
    -0.13
     Lone
    -0.13
    stag
    -0.12
     доÑģÑĤÑĥп
    -0.12
     bidi
    -0.12
    POSITIVE LOGITS
     normal
    0.77
    normal
    0.64
     Normal
    0.62
     NORMAL
    0.59
    -normal
    0.58
    Normal
    0.57
    æŃ£å¸¸
    0.56
     normals
    0.53
    .normal
    0.50
    _normal
    0.50
    Activations Density 0.066%

    No Known Activations