© 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. 24131
    Prev
    Next
    INDEX
    Explanations

    superlative and comparative adjectives

    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
     nowhere
    -0.20
    nen
    -0.19
     NEVER
    -0.16
    _deinit
    -0.15
    eree
    -0.15
     immediately
    -0.14
     nobody
    -0.14
     neither
    -0.13
     specifically
    -0.13
     Monk
    -0.13
    POSITIVE LOGITS
     almost
    0.78
    almost
    0.71
     nearly
    0.67
     Almost
    0.66
     virtually
    0.64
    Almost
    0.63
     Nearly
    0.58
    Nearly
    0.53
    åĩłä¹İ
    0.52
     pretty
    0.49
    Activations Density 0.028%

    No Known Activations