© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 29114
    Prev
    Next
    INDEX
    Explanations

    URLs and links shared in the text

    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
     wik
    -0.17
    ikip
    -0.17
    ,
    -0.16
    orns
    -0.15
    uai
    -0.15
    iffies
    -0.14
     Wik
    -0.14
    ugs
    -0.14
    eki
    -0.14
    ling
    -0.14
    POSITIVE LOGITS
    .twimg
    0.25
    twitter
    0.21
     twitter
    0.19
     twe
    0.19
    _tweet
    0.18
    bit
    0.18
    pbs
    0.17
    aje
    0.17
    Twitter
    0.17
     tweet
    0.17
    Activations Density 0.007%

    No Known Activations