© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 42674
    Prev
    Next
    INDEX
    Explanations

    instances of present tense verbs and their forms in relation to actions or descriptions

    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
    ambi
    -0.16
    ÏģÏİν
    -0.15
    à¸Ĭ
    -0.15
    iren
    -0.14
    igkeit
    -0.14
     tiener
    -0.14
    oodles
    -0.14
    ivor
    -0.14
    หาย
    -0.13
    asıyla
    -0.13
    POSITIVE LOGITS
     close
    0.54
     near
    0.46
    close
    0.44
     Close
    0.43
     CLOSE
    0.42
    Close
    0.41
    à¹ĥà¸ģล
    0.40
     nearly
    0.39
    -close
    0.39
     almost
    0.39
    Activations Density 0.034%

    No Known Activations