© 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 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. 14466
    Prev
    Next
    INDEX
    Explanations

    high percentages, particularly related to purity and achievement outcomes

    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
    ëį°
    -0.23
    ings
    -0.19
    iegel
    -0.17
    eren
    -0.17
    ness
    -0.16
    tons
    -0.16
    eds
    -0.16
    çĦ¶
    -0.16
    รวม
    -0.15
    IRROR
    -0.15
    POSITIVE LOGITS
    een
    0.32
    eenth
    0.31
    eros
    0.17
    istrovstvÃŃ
    0.17
    888
    0.17
    adero
    0.16
    ../../
    0.15
    571
    0.15
    iolet
    0.15
    μÏĢο
    0.15
    Activations Density 0.112%

    No Known Activations