© 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. 41658
    Prev
    Next
    INDEX
    Explanations

    phrases related to hypotheses and explanations in academic or analytical discussions

    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
    nga
    -0.15
    yen
    -0.14
    ild
    -0.13
    OffsetTable
    -0.13
    gement
    -0.13
     Guy
    -0.13
    HN
    -0.13
    ضÙĦ
    -0.13
    voj
    -0.12
    ighthouse
    -0.12
    POSITIVE LOGITS
     explain
    0.99
     explanation
    0.94
     explaining
    0.93
     explains
    0.93
     explanations
    0.88
     explained
    0.85
     Explain
    0.81
     Explanation
    0.80
    explain
    0.79
    Explanation
    0.74
    Activations Density 0.034%

    No Known Activations