© 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 EvalsExportsinterp-engineNEWAPI 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. 25132
    Prev
    Next
    INDEX
    Explanations

    phrases related to probabilities and analysis of large datasets

    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
    aver
    -0.14
     vind
    -0.14
    apia
    -0.14
    age
    -0.13
     yard
    -0.13
    authenticated
    -0.13
     proxy
    -0.13
     jenter
    -0.13
    наÑħ
    -0.13
     kil
    -0.13
    POSITIVE LOGITS
     possible
    0.54
     possibilities
    0.48
    possible
    0.45
     possibile
    0.44
     posible
    0.42
     Possible
    0.42
    Possible
    0.39
    åı¯èĥ½
    0.38
     possibility
    0.36
     POSS
    0.35
    Activations Density 0.059%

    No Known Activations