© 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. 53923
    Prev
    Next
    INDEX
    Explanations

    references to ancient artifacts, particularly pictographs and fossils

    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
     flagship
    -0.14
    akan
    -0.14
    anker
    -0.14
     undisclosed
    -0.13
     unspecified
    -0.13
    妮
    -0.13
     rare
    -0.13
    apper
    -0.12
    rels
    -0.12
     uncommon
    -0.12
    POSITIVE LOGITS
     known
    0.41
    known
    0.36
     Known
    0.34
     recorded
    0.34
    -known
    0.32
    -record
    0.29
    Known
    0.29
     surviving
    0.28
    record
    0.27
     Recorded
    0.26
    Activations Density 0.070%

    No Known Activations