© 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. 22578
    Prev
    Next
    INDEX
    Explanations

    temporal references related to durations and time frames

    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
    /Instruction
    -0.18
    _HELPER
    -0.17
    663
    -0.14
     пеÑĢеп
    -0.14
    aliz
    -0.14
     Else
    -0.13
     sebe
    -0.13
    alin
    -0.13
     elsewhere
    -0.13
    ìŀĦ
    -0.13
    POSITIVE LOGITS
     after
    0.58
    after
    0.41
     dopo
    0.40
     поÑģле
    0.36
     After
    0.36
    _after
    0.36
     após
    0.35
     después
    0.34
    After
    0.34
     efter
    0.34
    Activations Density 0.042%

    No Known Activations