© 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. 24420
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns related to participation and experiences in activities

    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
    ãģķãĤĵãģĮ
    -0.14
    inceton
    -0.14
    ác
    -0.14
    á»ķ
    -0.14
    tom
    -0.14
     CircularProgress
    -0.14
    ubb
    -0.14
    holm
    -0.14
    .utf
    -0.13
     setTitleColor
    -0.13
    POSITIVE LOGITS
     with
    0.92
    with
    0.74
     avec
    0.66
     vỼi
    0.64
     WITH
    0.61
     With
    0.59
     dengan
    0.59
    	with
    0.58
    _with
    0.56
    ewith
    0.52
    Activations Density 0.073%

    No Known Activations