© 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. 23825
    Prev
    Next
    INDEX
    Explanations

    discussions about educational support and independence for students

    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
    egin
    -0.16
    swers
    -0.14
    anton
    -0.13
    Survey
    -0.13
    .wrap
    -0.13
    spd
    -0.13
    icher
    -0.12
    سÙĨ
    -0.12
    IFA
    -0.12
    onical
    -0.12
    POSITIVE LOGITS
     success
    0.49
     succeed
    0.48
     Success
    0.41
     succeeds
    0.41
    success
    0.40
    ucceed
    0.39
    Success
    0.39
     succeeded
    0.39
     excel
    0.35
     successful
    0.34
    Activations Density 0.125%

    No Known Activations