© 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. 44431
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or observations of movement and advancement

    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
    atus
    -0.15
    ?url
    -0.15
    .removeEventListener
    -0.14
    alse
    -0.14
    ite
    -0.14
     Prest
    -0.14
    .Scene
    -0.14
    ocos
    -0.14
     lookup
    -0.14
    andon
    -0.13
    POSITIVE LOGITS
     approach
    0.66
    appro
    0.61
     Approach
    0.61
     approaches
    0.58
     approached
    0.56
    Appro
    0.55
     approaching
    0.54
     Appro
    0.53
     APPRO
    0.48
     appro
    0.44
    Activations Density 0.028%

    No Known Activations