© 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. 23971
    Prev
    Next
    INDEX
    Explanations

    references to the concept of freedom and its implications

    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
    ccione
    -0.15
    flux
    -0.14
    olvency
    -0.14
    ุà¸ĩ
    -0.14
    veau
    -0.14
     MatSnackBar
    -0.14
    lemetry
    -0.13
    xcc
    -0.13
    dlg
    -0.13
    arna
    -0.13
    POSITIVE LOGITS
     fight
    1.27
     Fight
    1.15
    fight
    1.14
    Fight
    1.13
     fighting
    1.13
     fights
    1.07
     Fighting
    0.99
     fought
    0.97
     fighters
    0.92
     fighter
    0.89
    Activations Density 0.009%

    No Known Activations