© 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. 15719
    Prev
    Next
    INDEX
    Explanations

    measurements or units of distance and height

    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
    .cm
    -0.19
     CM
    -0.17
    -meter
    -0.16
     (
    -0.16
     ("
    -0.16
    illion
    -0.15
     cm
    -0.15
    (cm
    -0.15
    meter
    -0.15
     Meter
    -0.15
    POSITIVE LOGITS
    -US
    0.17
     Mỹ
    0.17
     US
    0.16
     imperial
    0.15
     ç¾İåĽ½
    0.15
     Americans
    0.15
    US
    0.15
     Amerika
    0.15
    ç¾İ
    0.15
     СШÐIJ
    0.15
    Activations Density 0.048%

    No Known Activations