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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 23851
    Prev
    Next
    INDEX
    Explanations

    references to government or administrative actions and issues related to regulation or oversight

    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
     defe
    -0.17
    unbind
    -0.16
    atter
    -0.15
    ż
    -0.14
    olet
    -0.14
     Dart
    -0.14
    ativ
    -0.14
    ateurs
    -0.14
    opyright
    -0.14
    ATTER
    -0.14
    POSITIVE LOGITS
     hiding
    0.47
     conceal
    0.47
     hides
    0.40
     hid
    0.40
     Conce
    0.39
     hide
    0.38
     concealed
    0.36
     Hide
    0.36
     conce
    0.36
     hidden
    0.34
    Activations Density 0.056%

    No Known Activations