© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 63492
    Prev
    Next
    INDEX
    Explanations

    references to security vulnerabilities and affected devices

    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
    ÙĨدگاÙĨ
    -0.16
    adt
    -0.15
    avl
    -0.15
    omics
    -0.14
    olib
    -0.14
    uga
    -0.14
    ijke
    -0.13
    hl
    -0.13
    ynch
    -0.13
     TIMEOUT
    -0.13
    POSITIVE LOGITS
     affected
    1.03
    affected
    0.92
    Affected
    0.82
     afect
    0.70
     affect
    0.66
     affects
    0.60
     impacted
    0.58
     effected
    0.55
     unaffected
    0.54
    FFECT
    0.48
    Activations Density 0.082%

    No Known Activations