© 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. 9025
    Prev
    Next
    INDEX
    Explanations

    contrastive phrases that introduce a distinction or alternative perspective

    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
    ertest
    -0.16
     không
    -0.15
     NOT
    -0.14
     donc
    -0.14
     tidak
    -0.14
    olio
    -0.14
    ilities
    -0.14
    idak
    -0.13
     notamment
    -0.13
     ÙĨدار
    -0.13
    POSITIVE LOGITS
     rather
    0.97
     Rather
    0.80
    rather
    0.80
    Rather
    0.75
     instead
    0.61
     Instead
    0.51
    Instead
    0.49
     plutôt
    0.48
    instead
    0.47
     spÃŃÅ¡e
    0.38
    Activations Density 0.062%

    No Known Activations