© 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
    3. Julius Han · Gated SAE for Llama3-8B-Instruct
    5. Llama3-8B-IT
    7. Residual Stream
    9. 25-RES-JH
    11. 29713
    Prev
    Next
    INDEX
    Explanations

    instances of the word "of" in various 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
     somehow
    -0.16
     mere
    -0.15
    orem
    -0.15
    athers
    -0.15
    remely
    -0.14
    riz
    -0.14
     cumshot
    -0.14
    nt
    -0.14
    еÑĢÑĪ
    -0.14
     suche
    -0.14
    POSITIVE LOGITS
     like
    0.28
    -sort
    0.25
     Like
    0.23
     LIKE
    0.21
    Like
    0.19
    like
    0.18
    antity
    0.17
    _like
    0.17
     thing
    0.16
    thing
    0.15
    Activations Density 0.021%

    No Known Activations