© 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. 42140
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and regulatory issues

    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
    ERICA
    -0.15
    -scrollbar
    -0.15
    esinin
    -0.15
    .toolbox
    -0.15
    ázev
    -0.14
    Latch
    -0.14
    ÑĤÑĢо
    -0.14
    vanished
    -0.14
    ÎŃÏģα
    -0.13
    .omg
    -0.13
    POSITIVE LOGITS
    æİī
    0.16
    ments
    0.16
    issement
    0.15
    ation
    0.15
    аниÑĨ
    0.15
    ishment
    0.15
    ment
    0.14
    /null
    0.13
    lation
    0.13
    ibility
    0.13
    Activations Density 0.032%

    No Known Activations