© 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. 41089
    Prev
    Next
    INDEX
    Explanations

    references to historical or literary figures and their works

    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
    quee
    -0.15
    ÃŃcia
    -0.14
    ENTIC
    -0.14
    Atomic
    -0.14
    áv
    -0.14
    صÙĪر
    -0.14
    endir
    -0.14
    ergy
    -0.14
    .writ
    -0.14
     nhân
    -0.14
    POSITIVE LOGITS
    .uni
    0.15
    ãĥ¼ãĥī
    0.15
    pace
    0.15
    855
    0.14
     pace
    0.14
     Manit
    0.14
     Oman
    0.13
     Hüs
    0.13
    mgr
    0.13
    inus
    0.13
    Activations Density 0.019%

    No Known Activations