© 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. 55303
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" and related verbs indicating intention or action

    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
     forn
    -0.14
     consolid
    -0.14
     banner
    -0.14
     
    -0.13
    лек
    -0.13
    antly
    -0.13
     consolidation
    -0.13
     found
    -0.13
     cr
    -0.13
     Äijâu
    -0.13
    POSITIVE LOGITS
     proceed
    0.24
     Proceed
    0.22
     best
    0.20
     approached
    0.20
    Proceed
    0.20
     approach
    0.20
     proceeded
    0.20
    best
    0.19
     proceeds
    0.18
     Approach
    0.17
    Activations Density 0.096%

    No Known Activations