© 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. 8775
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups of people in a context of evaluation or critique

    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
     two
    -0.21
     three
    -0.18
     entirety
    -0.18
    two
    -0.18
     zwei
    -0.17
    three
    -0.16
    两
    -0.16
    两个
    -0.16
     presence
    -0.15
     entire
    -0.15
    POSITIVE LOGITS
     same
    0.25
     most
    0.24
     earliest
    0.22
     more
    0.21
     misma
    0.20
     other
    0.20
     early
    0.19
     earlier
    0.19
     newer
    0.19
     later
    0.18
    Activations Density 0.078%

    No Known Activations