© 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. 63216
    Prev
    Next
    INDEX
    Explanations

    instances of quantified comparisons and elements of measurement

    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
    ATCH
    -0.13
     tomorrow
    -0.13
    ÏĦηÏĤ
    -0.13
    desc
    -0.13
     
    -0.13
    incinn
    -0.12
     affairs
    -0.12
    _LP
    -0.12
     vain
    -0.12
    .Payload
    -0.12
    POSITIVE LOGITS
     amount
    0.32
     lack
    0.30
     fact
    0.28
     sheer
    0.28
     combination
    0.26
     way
    0.25
     presence
    0.25
     increased
    0.24
    fact
    0.24
     unusual
    0.23
    Activations Density 0.279%

    No Known Activations