© 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. 21990
    Prev
    Next
    INDEX
    Explanations

    references to people’s occupations and significant events

    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
    202
    -0.13
    Hint
    -0.13
    abile
    -0.13
    ervo
    -0.13
    oose
    -0.13
    pNet
    -0.13
    lesi
    -0.12
     addCriterion
    -0.12
    365
    -0.12
     candidacy
    -0.12
    POSITIVE LOGITS
    iev
    0.15
    ]=>
    0.14
    à¤Ĥà¤ľà¤¨
    0.13
    ema
    0.13
    anton
    0.12
    .jasper
    0.12
    entin
    0.12
    ior
    0.12
    \f
    0.11
    ụn
    0.11
    Activations Density 0.072%

    No Known Activations