© 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. 15571
    Prev
    Next
    INDEX
    Explanations

    references to organizations and platforms focused on truth and transparency

    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
    ween
    -0.13
    indsight
    -0.13
    amework
    -0.13
    getMock
    -0.13
    _ALWAYS
    -0.13
    AXB
    -0.13
     continue
    -0.13
    illow
    -0.12
    tember
    -0.12
    oplayer
    -0.12
    POSITIVE LOGITS
     hopes
    0.35
     hope
    0.34
     hoped
    0.30
     hoping
    0.29
     aims
    0.28
     aim
    0.28
     ultimate
    0.28
     plan
    0.28
     goal
    0.27
     ultimately
    0.25
    Activations Density 0.039%

    No Known Activations