© 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. 9043
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of individuals

    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
    Č
    -0.15
    ylon
    -0.14
    :
    -0.14
    iguous
    -0.14
     fig
    -0.13
    achu
    -0.13
     hundreds
    -0.13
    Ŀ
    -0.13
    alist
    -0.13
    ordova
    -0.13
    POSITIVE LOGITS
     age
    0.40
     aged
    0.38
    age
    0.31
    34
    0.31
    29
    0.31
    36
    0.31
    -age
    0.31
    32
    0.30
     ages
    0.30
    35
    0.30
    Activations Density 0.052%

    No Known Activations