© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 30612
    Prev
    Next
    INDEX
    Explanations

    geographical locations and natural features in British Columbia and surrounding regions

    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
     Shore
    -0.18
    anker
    -0.14
     Harbour
    -0.13
    -vertical
    -0.13
     pitch
    -0.13
     Cliff
    -0.13
     serg
    -0.12
    prod
    -0.12
     kolo
    -0.12
    RTC
    -0.12
    POSITIVE LOGITS
     portion
    0.20
     north
    0.18
     west
    0.18
     portions
    0.18
     along
    0.18
     south
    0.17
     Portions
    0.17
     drained
    0.17
     east
    0.16
     parts
    0.16
    Activations Density 0.199%

    No Known Activations