© 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. 13502
    Prev
    Next
    INDEX
    Explanations

    references to legal charges and investigations

    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
    ior
    -0.16
     nÃło
    -0.14
    abbo
    -0.14
    oir
    -0.14
    eniable
    -0.14
    ;;;;;;;;;;;;;;;;
    -0.14
    keh
    -0.14
     münchen
    -0.14
    WithError
    -0.14
    wand
    -0.13
    POSITIVE LOGITS
     including
    0.71
    including
    0.61
     Including
    0.58
    åĮħæĭ¬
    0.54
    Including
    0.52
     INCLUDING
    0.50
     vÄįetnÄĽ
    0.47
     includ
    0.45
    cluding
    0.43
     incl
    0.42
    Activations Density 0.146%

    No Known Activations