© 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. 15441
    Prev
    Next
    INDEX
    Explanations

    themes of violence and state-sanctioned actions

    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
     achie
    -0.15
     اصÙģÙĩ
    -0.14
     INCIDENT
    -0.14
     sympath
    -0.13
     incons
    -0.13
    од
    -0.13
     assail
    -0.13
     exempt
    -0.13
     پرد
    -0.13
     Crest
    -0.13
    POSITIVE LOGITS
     kid
    0.18
    entic
    0.18
     downright
    0.18
     intimidation
    0.18
     bullying
    0.17
     sabotage
    0.17
     distortion
    0.17
     Tort
    0.17
    repr
    0.17
     ambush
    0.16
    Activations Density 0.024%

    No Known Activations