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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 63325
    Prev
    Next
    INDEX
    Explanations

    possessive forms and reflections on personal experiences

    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
    asca
    -0.17
     éĢ
    -0.15
    707
    -0.14
    Submitted
    -0.14
    à¸İ
    -0.14
    .EventHandler
    -0.14
     pourrait
    -0.14
    çħ§
    -0.13
    ãģıãĤĭ
    -0.13
    quer
    -0.13
    POSITIVE LOGITS
     been
    0.65
     Been
    0.52
    been
    0.52
    Been
    0.49
     BEEN
    0.46
     become
    0.37
     sido
    0.31
     come
    0.30
     été
    0.29
     gone
    0.26
    Activations Density 0.063%

    No Known Activations