© 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 EvalsExportsinterp-engineNEWAPI 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. 43514
    Prev
    Next
    INDEX
    Explanations

    phrases related to climbing and summiting peaks

    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
    ãĤ¤ãĥ³ãĥĪ
    -0.15
    quina
    -0.15
    \Blueprint
    -0.14
    imar
    -0.14
    lycer
    -0.14
     endwhile
    -0.14
    robat
    -0.13
    ssi
    -0.13
    lector
    -0.13
    ãĤ±ãĥĥãĥĪ
    -0.13
    POSITIVE LOGITS
     for
    0.73
    for
    0.58
    	for
    0.47
     For
    0.45
     voor
    0.43
    For
    0.42
     för
    0.42
     untuk
    0.41
     για
    0.39
     für
    0.39
    Activations Density 0.024%

    No Known Activations