© 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. 41134
    Prev
    Next
    INDEX
    Explanations

    words that contain the letter combination "i"

    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
    ÑģÑĮ
    -0.15
    )prepare
    -0.14
    erif
    -0.14
    xaa
    -0.14
    RuleContext
    -0.14
    .='
    -0.14
    omap
    -0.14
    anst
    -0.14
    .ERR
    -0.14
    alach
    -0.14
    POSITIVE LOGITS
     Jr
    0.22
     who
    0.21
     III
    0.19
    who
    0.18
     recently
    0.18
     whose
    0.17
    åįļ士
    0.16
     PhD
    0.16
     yesterday
    0.15
    âĢ¦
    0.15
    Activations Density 0.257%

    No Known Activations