© 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. 29553
    Prev
    Next
    INDEX
    Explanations

    references to dubious health practices or pseudoscience

    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
     hypoc
    -0.15
     Slut
    -0.15
    ronic
    -0.15
    631
    -0.14
    178
    -0.14
    .nih
    -0.14
    éı
    -0.13
    .va
    -0.13
     atheist
    -0.13
     conservative
    -0.13
    POSITIVE LOGITS
     fringe
    0.32
     crack
    0.31
     nut
    0.28
     pseud
    0.26
     extreme
    0.25
     crank
    0.25
    nut
    0.24
     lun
    0.22
     qu
    0.22
     extremes
    0.21
    Activations Density 0.098%

    No Known Activations