© 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. 41306
    Prev
    Next
    INDEX
    Explanations

    references to virtual networks and privacy considerations

    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
    667
    -0.13
    666
    -0.13
    iture
    -0.13
     XHTML
    -0.13
    à¸ĵ
    -0.13
    ucid
    -0.13
    é«ĺæ¸ħ
    -0.13
    amento
    -0.13
    adan
    -0.13
    inger
    -0.13
    POSITIVE LOGITS
     third
    0.55
    third
    0.47
    第ä¸ī
    0.42
     THIRD
    0.40
    Third
    0.39
     Third
    0.38
     第ä¸ī
    0.37
    -third
    0.35
    _third
    0.34
     external
    0.32
    Activations Density 0.144%

    No Known Activations