© 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. 21743
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditionality or causation

    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
     evidenced
    -0.16
    mob
    -0.14
    errat
    -0.14
    omo
    -0.14
     lah
    -0.14
    ohn
    -0.14
    unan
    -0.14
    tvrt
    -0.14
    ucch
    -0.14
    cil
    -0.14
    POSITIVE LOGITS
     part
    0.42
     required
    0.24
    part
    0.23
     soon
    0.21
     parte
    0.21
     ÑĩаÑģÑĤÑĮ
    0.21
    _part
    0.21
     per
    0.19
     Required
    0.18
     بخشÛĮ
    0.18
    Activations Density 0.101%

    No Known Activations