© 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. 13561
    Prev
    Next
    INDEX
    Explanations

    instances of uncertainty or suspicion in narratives

    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
     never
    -0.15
    ilog
    -0.14
    .TabIndex
    -0.14
    ovo
    -0.14
    wap
    -0.13
    arial
    -0.13
    à¹īาร
    -0.13
    rezent
    -0.13
    éĤ£æł·
    -0.13
     way
    -0.13
    POSITIVE LOGITS
     begins
    0.23
     truly
    0.23
     really
    0.22
     rubber
    0.22
    羣æŃ£
    0.21
     enters
    0.21
     true
    0.20
     vraiment
    0.20
     羣
    0.19
    Really
    0.19
    Activations Density 0.027%

    No Known Activations