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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 25097
    Prev
    Next
    INDEX
    Explanations

    negative phrases related to existence or presence

    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
     not
    -0.29
     niet
    -0.22
     nicht
    -0.21
     ikke
    -0.21
     não
    -0.21
     no
    -0.19
     NOT
    -0.18
     không
    -0.18
     не
    -0.18
    Not
    -0.17
    POSITIVE LOGITS
     necessarily
    0.29
    epad
    0.29
    tingham
    0.24
    icable
    0.23
    ched
    0.23
     longer
    0.23
    ches
    0.22
     yet
    0.22
    ori
    0.22
    ional
    0.22
    Activations Density 0.264%

    No Known Activations