© 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. 54153
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "the" across different contexts

    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
     overall
    -0.19
    enden
    -0.16
    DAQ
    -0.15
    ivities
    -0.15
    Overall
    -0.14
    ãĥĵãĥ¼
    -0.14
    asted
    -0.14
    opup
    -0.13
     actual
    -0.13
    ALSE
    -0.13
    POSITIVE LOGITS
     result
    0.32
     Result
    0.24
     combination
    0.24
    result
    0.24
    oret
    0.23
    orem
    0.23
     proof
    0.23
    .result
    0.22
    (result
    0.22
     reason
    0.22
    Activations Density 0.039%

    No Known Activations