© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12440
    Prev
    Next
    INDEX
    Explanations

    phrases indicating personal concerns or considerations in a context

    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
    ertain
    -0.14
    mma
    -0.14
     treff
    -0.14
    .ly
    -0.14
    rices
    -0.14
    .FontStyle
    -0.13
    (çģ«
    -0.13
     даже
    -0.13
     tháºŃm
    -0.13
    orrect
    -0.13
    POSITIVE LOGITS
     myself
    0.29
     whether
    0.26
     why
    0.26
     other
    0.25
    æĺ¯åIJ¦
    0.22
     specific
    0.21
     specifically
    0.21
     yourself
    0.21
     actual
    0.20
    why
    0.20
    Activations Density 0.089%

    No Known Activations