© 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. 8588
    Prev
    Next
    INDEX
    Explanations

    expressions related to making sense or logical coherence

    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
    oir
    -0.15
    aceous
    -0.14
    une
    -0.14
    -FIRST
    -0.14
     Nothing
    -0.14
    ziel
    -0.14
    nothing
    -0.13
    ulle
    -0.13
     adım
    -0.13
    çıł
    -0.13
    POSITIVE LOGITS
     sense
    0.67
     Sense
    0.51
    sense
    0.49
    Sense
    0.47
     sentido
    0.39
     senses
    0.36
     sensed
    0.28
    cents
    0.24
    ense
    0.24
    SEN
    0.23
    Activations Density 0.019%

    No Known Activations