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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23603
    Prev
    Next
    INDEX
    Explanations

    references to screens and their specifications

    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
    /ay
    -0.15
    nt
    -0.15
    γκ
    -0.14
    axon
    -0.14
    ufe
    -0.14
     th
    -0.14
    Broad
    -0.14
    nes
    -0.14
     the
    -0.14
    umbles
    -0.13
    POSITIVE LOGITS
     saver
    0.20
     resolution
    0.19
    å¹ķ
    0.19
    _Real
    0.18
     resolutions
    0.18
    avers
    0.17
    resolution
    0.17
     estate
    0.17
    Resolution
    0.17
    estate
    0.16
    Activations Density 0.033%

    No Known Activations