© 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. 8856
    Prev
    Next
    INDEX
    Explanations

    terms related to explicit and implicit memory concepts

    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
    yonel
    -0.17
    arde
    -0.17
    รม
    -0.16
    ladu
    -0.15
    ipment
    -0.15
    -ÑĤо
    -0.15
    ä¿
    -0.15
    ÑĦекÑĤив
    -0.15
    iÄįky
    -0.15
    istique
    -0.15
    POSITIVE LOGITS
    ely
    0.42
    ly
    0.30
    ELY
    0.27
    ness
    0.23
    /exp
    0.21
     mention
    0.20
    elly
    0.19
    urn
    0.19
    ively
    0.19
    mente
    0.18
    Activations Density 0.010%

    No Known Activations