© 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. 23826
    Prev
    Next
    INDEX
    Explanations

    references to individual identity and credentials within the context of explaining a topic

    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
     simply
    -0.27
     just
    -0.24
     already
    -0.22
     Simply
    -0.21
     also
    -0.20
    Already
    -0.19
     Already
    -0.19
     simplement
    -0.19
    åıĪ
    -0.19
     пÑĢоÑģÑĤо
    -0.19
    POSITIVE LOGITS
     truly
    0.34
     ever
    0.28
     Truly
    0.27
     really
    0.27
    羣æŃ£
    0.24
    really
    0.23
     anymore
    0.23
     EVER
    0.23
     wirklich
    0.22
     remaining
    0.22
    Activations Density 0.043%

    No Known Activations