© 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. 9125
    Prev
    Next
    INDEX
    Explanations

    references to academic contributions and their impact on the field

    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
     Schul
    -0.16
     studi
    -0.15
     studies
    -0.15
    -=
    -0.14
     Dex
    -0.14
    Studies
    -0.14
     Studies
    -0.14
    -transitional
    -0.14
    -spacing
    -0.14
    ÏĥÏį
    -0.14
    POSITIVE LOGITS
     NSF
    0.20
     referee
    0.17
    Collider
    0.17
    TeX
    0.17
     Classics
    0.17
    Pointer
    0.16
     papers
    0.16
    omics
    0.14
    WISE
    0.14
     Lisp
    0.14
    Activations Density 0.049%

    No Known Activations