© 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
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 63849
    Prev
    Next
    INDEX
    Explanations

    references to technological partnerships and communication frameworks

    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
    tes
    -0.17
    äºĭ
    -0.17
     ATM
    -0.14
    raud
    -0.14
     Hans
    -0.14
     Rao
    -0.14
    erior
    -0.14
    resco
    -0.13
     mushroom
    -0.13
     Mari
    -0.13
    POSITIVE LOGITS
    jab
    0.28
     Jab
    0.25
     Presence
    0.23
    presence
    0.23
     presence
    0.22
    xm
    0.22
    Presence
    0.22
     xm
    0.21
     feder
    0.21
    .habbo
    0.21
    Activations Density 0.012%

    No Known Activations