© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63553
    Prev
    Next
    INDEX
    Explanations

    terms related to meteors and meteorology

    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
    eners
    -0.18
    nothrow
    -0.17
    ARSE
    -0.15
    spiel
    -0.15
    iliar
    -0.15
    Ïģαβ
    -0.15
    eline
    -0.15
    sWith
    -0.15
    tures
    -0.15
    _FC
    -0.14
    POSITIVE LOGITS
    oid
    0.28
    ite
    0.28
    ological
    0.27
     showers
    0.26
     shower
    0.26
    oids
    0.25
    itical
    0.24
    ites
    0.24
     Shower
    0.24
    logical
    0.22
    Activations Density 0.005%

    No Known Activations