© 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. 33048
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions of time and performance metrics

    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
    oot
    -0.16
     Blackburn
    -0.15
    Sha
    -0.14
    Resume
    -0.14
     Dawn
    -0.14
     æ½
    -0.13
     Sha
    -0.13
    ož
    -0.13
    akk
    -0.13
     MIL
    -0.13
    POSITIVE LOGITS
     quarter
    0.66
     quarters
    0.55
     Quarter
    0.49
    quarter
    0.46
    Quarter
    0.44
    -quarter
    0.43
    quarters
    0.37
     quarterly
    0.31
    -quarters
    0.29
     month
    0.28
    Activations Density 0.075%

    No Known Activations