© 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. 29709
    Prev
    Next
    INDEX
    Explanations

    references to local wildlife and their habitats

    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
     Stay
    -0.16
    ldre
    -0.16
    rego
    -0.15
    ména
    -0.15
    úsqueda
    -0.14
    uling
    -0.14
    Stay
    -0.14
     swal
    -0.14
    @update
    -0.14
    nton
    -0.14
    POSITIVE LOGITS
     call
    0.62
     calls
    0.54
    call
    0.51
     Call
    0.49
     calling
    0.49
    Call
    0.48
     Calls
    0.47
     CALL
    0.47
    calls
    0.46
    .call
    0.45
    Activations Density 0.036%

    No Known Activations