© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 55039
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement and crime-related activities

    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
    PasswordEncoder
    -0.17
    ácil
    -0.17
     äºĭ
    -0.16
     lesb
    -0.15
    .setViewport
    -0.15
     assass
    -0.15
    .EventType
    -0.15
    atcher
    -0.14
    ìĮ
    -0.14
     Rape
    -0.14
    POSITIVE LOGITS
     organized
    0.21
     gang
    0.20
     straw
    0.20
     repeat
    0.20
     prolific
    0.19
     synthetic
    0.19
     наÑĢ
    0.18
     predicate
    0.17
     gangs
    0.17
     meth
    0.17
    Activations Density 0.052%

    No Known Activations