© 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. 44411
    Prev
    Next
    INDEX
    Explanations

    information related to education and its policies

    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
    anio
    -0.16
    itto
    -0.13
    prepend
    -0.13
     someday
    -0.13
    adal
    -0.13
     Tomorrow
    -0.13
     elsewhere
    -0.12
    indle
    -0.12
    ilos
    -0.12
    orris
    -0.12
    POSITIVE LOGITS
     after
    1.07
    after
    0.86
     After
    0.76
    After
    0.75
     dopo
    0.74
     AFTER
    0.73
     поÑģле
    0.70
    _after
    0.70
     après
    0.65
     efter
    0.65
    Activations Density 0.077%

    No Known Activations