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

    Neuronpedia

    Jacobian LensNEW
    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. 14448
    Prev
    Next
    INDEX
    Explanations

    descriptions of natural landscapes and coastal environments

    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
     pond
    -0.16
     gord
    -0.16
    åľ³
    -0.16
     lakes
    -0.15
     Schwe
    -0.15
    åľ°ä¸ĭ
    -0.15
     canoe
    -0.14
    erais
    -0.14
    éij
    -0.14
     corridors
    -0.14
    POSITIVE LOGITS
     beach
    0.48
     Beach
    0.42
     beaches
    0.41
     tide
    0.34
     surf
    0.34
     sands
    0.31
     sand
    0.31
     coast
    0.28
     tidal
    0.28
     waves
    0.26
    Activations Density 0.030%

    No Known Activations