© 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. 54842
    Prev
    Next
    INDEX
    Explanations

    references to personal relationships and collaborative efforts

    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
     was
    -0.21
     finally
    -0.18
     were
    -0.18
     wasn
    -0.18
     had
    -0.17
     yourself
    -0.17
     your
    -0.17
     didn
    -0.16
     potentially
    -0.16
    kker
    -0.16
    POSITIVE LOGITS
     sometimes
    0.49
    sometimes
    0.44
     Sometimes
    0.42
    ometimes
    0.41
    Sometimes
    0.40
     lately
    0.38
     usually
    0.36
     occasionally
    0.36
     often
    0.34
    usually
    0.34
    Activations Density 0.066%

    No Known Activations