© 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. 41329
    Prev
    Next
    INDEX
    Explanations

    statistical trends regarding crime rates and incidents

    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
    (++
    -0.22
     aumento
    -0.21
     incremented
    -0.21
     ++$
    -0.20
    å¢Ĺ
    -0.20
     (++
    -0.20
     increase
    -0.20
    [++
    -0.19
    涨
    -0.19
     zvý
    -0.19
    POSITIVE LOGITS
     reduced
    0.38
     reductions
    0.35
     reduction
    0.35
     reduce
    0.34
     reducing
    0.33
     reduces
    0.33
     Reduction
    0.31
     Reduced
    0.30
     Reduce
    0.30
    reduce
    0.30
    Activations Density 0.073%

    No Known Activations