© 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. 63586
    Prev
    Next
    INDEX
    Explanations

    references to appendices or supplementary materials in a document

    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
     CircularProgress
    -0.16
    ازÙĩ
    -0.12
     Hastings
    -0.11
     proof
    -0.11
     overse
    -0.11
    ä½ľèĢħ
    -0.11
     maybe
    -0.11
    ÑĸлÑĮ
    -0.11
     Illustr
    -0.11
     thinking
    -0.11
    POSITIVE LOGITS
    -BEGIN
    0.14
     докÑĥм
    0.14
    AndHashCode
    0.14
    ropa
    0.14
    TOTYPE
    0.14
    ¶ģ
    0.13
     Qed
    0.13
     곧
    0.13
     ëĵľë¦½ëĭĪëĭ¤
    0.13
    ãĤīãģĦ
    0.13
    Activations Density 0.153%

    No Known Activations