© 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. 42015
    Prev
    Next
    INDEX
    Explanations

    phrases and constructions indicating negation or absence

    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
    nap
    -0.14
    entes
    -0.14
    sy
    -0.13
     hopes
    -0.13
    rys
    -0.13
    uran
    -0.13
    ony
    -0.13
     hope
    -0.12
     hoping
    -0.12
    ki
    -0.12
    POSITIVE LOGITS
     need
    0.86
     Need
    0.76
     needed
    0.75
    need
    0.73
     needing
    0.70
    Need
    0.69
     necessity
    0.69
     NEED
    0.67
     needs
    0.67
    éľĢè¦ģ
    0.66
    Activations Density 0.004%

    No Known Activations