© 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. 28969
    Prev
    Next
    INDEX
    Explanations

    terms related to limitations or constraints

    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
    OrDefault
    -0.15
    awan
    -0.15
    obi
    -0.15
    NU
    -0.15
     disrupting
    -0.15
    stations
    -0.15
    oma
    -0.14
    fish
    -0.14
    ìĬ¤íģ¬
    -0.14
    лоÑĩ
    -0.14
    POSITIVE LOGITS
    .Restr
    0.22
    ively
    0.22
    ive
    0.21
    iveness
    0.20
    naire
    0.18
    ions
    0.16
    neck
    0.16
    tach
    0.15
    sdale
    0.15
    (equalTo
    0.15
    Activations Density 0.012%

    No Known Activations