© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14022
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "be" and related constructs indicating existence or condition

    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
    ior
    -0.14
    KERNEL
    -0.13
    du
    -0.13
    ansa
    -0.13
    imitives
    -0.13
     du
    -0.13
    IID
    -0.13
    기ëıĦ
    -0.13
    stant
    -0.13
    ABCDEFGHI
    -0.13
    POSITIVE LOGITS
     felt
    0.18
    gets
    0.18
     costly
    0.18
    get
    0.18
     counter
    0.18
     grounds
    0.18
    counter
    0.18
     beneficial
    0.17
     disastrous
    0.17
     cata
    0.17
    Activations Density 0.102%

    No Known Activations