© 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. 13239
    Prev
    Next
    INDEX
    Explanations

    references to travel restrictions and governmental policies related to Cuba

    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
    ENTA
    -0.17
    ettel
    -0.16
    937
    -0.15
    ubl
    -0.15
    Closure
    -0.14
     Closed
    -0.14
     Morr
    -0.14
    uste
    -0.14
    pons
    -0.14
     Closure
    -0.14
    POSITIVE LOGITS
     lift
    0.69
     lifting
    0.69
     lifted
    0.64
     lifts
    0.63
    lift
    0.59
     Lift
    0.59
     relaxation
    0.55
     relaxing
    0.54
     relaxed
    0.53
     relax
    0.53
    Activations Density 0.051%

    No Known Activations