© 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. 15477
    Prev
    Next
    INDEX
    Explanations

    possessive forms indicating ownership or belonging

    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
     when
    -0.14
    âk
    -0.13
     actually
    -0.13
    ooke
    -0.13
    ิ
    -0.12
     (
    -0.12
    .
    -0.12
     ones
    -0.12
     what
    -0.12
    early
    -0.12
    POSITIVE LOGITS
     these
    0.20
    these
    0.19
    è¿ĻäºĽ
    0.17
     latter
    0.16
     tyto
    0.15
     tÄĽchto
    0.15
    &oacute
    0.15
     ÑĨиÑħ
    0.15
     à¤ĩसस
    0.15
    _both
    0.14
    Activations Density 0.000%

    No Known Activations