© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 54804
    Prev
    Next
    INDEX
    Explanations

    variations of the word "particular" and its derivatives

    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
    okit
    -0.19
    ,readonly
    -0.16
     particular
    -0.16
     particulars
    -0.16
    enn
    -0.15
    ener
    -0.15
    eat
    -0.15
    æīį
    -0.14
    اء
    -0.14
    erties
    -0.14
    POSITIVE LOGITS
    ily
    0.33
    ity
    0.27
    mente
    0.25
    ities
    0.24
    ized
    0.24
    istic
    0.23
    ร
    0.20
    izing
    0.20
    .ly
    0.19
    ;y
    0.18
    Activations Density 0.029%

    No Known Activations