© 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. 14301
    Prev
    Next
    INDEX
    Explanations

    references to the year 1945

    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
    amen
    -0.17
    olum
    -0.15
    nila
    -0.15
    alach
    -0.15
    ospel
    -0.14
    serter
    -0.14
    eds
    -0.14
    ochen
    -0.14
    olor
    -0.14
    renched
    -0.13
    POSITIVE LOGITS
    o
    0.15
    ãĤ¤ãĥ«
    0.14
    unya
    0.14
    ÎķÎ¥
    0.14
    ALES
    0.13
    bir
    0.13
    -era
    0.13
    letion
    0.13
    алеж
    0.13
    ÛĮات
    0.13
    Activations Density 0.010%

    No Known Activations