© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23042
    Prev
    Next
    INDEX
    Explanations

    instances of collaboration and efforts made by individuals or groups to address issues

    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
     Obr
    -0.16
    antage
    -0.15
    íĥ
    -0.15
    ystone
    -0.15
    edException
    -0.14
    .Bunifu
    -0.14
    estroy
    -0.13
    ÛĮات
    -0.13
    ÃŃk
    -0.13
    ruits
    -0.13
    POSITIVE LOGITS
     encounter
    0.79
     faced
    0.73
     encounters
    0.70
     face
    0.67
     encountered
    0.67
     faces
    0.67
     facing
    0.64
    éģĩ
    0.62
     encountering
    0.61
     Encounter
    0.60
    Activations Density 0.064%

    No Known Activations