© 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. 24246
    Prev
    Next
    INDEX
    Explanations

    terms related to insecurity or vulnerabilities related to technology and systems

    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
    closest
    -0.15
     éł
    -0.14
    ãĥŃãĥ³
    -0.13
    quit
    -0.13
     åĢ
    -0.13
    iet
    -0.12
     piel
    -0.12
    uni
    -0.12
    _isr
    -0.12
     Presence
    -0.12
    POSITIVE LOGITS
     sake
    0.56
     purposes
    0.52
     purpose
    0.32
     benefit
    0.30
     foreseeable
    0.30
    purpose
    0.24
     reasons
    0.23
     duration
    0.22
     majority
    0.22
     meantime
    0.21
    Activations Density 0.240%

    No Known Activations