© 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. 14490
    Prev
    Next
    INDEX
    Explanations

    references to majorities and their influence in political contexts

    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
    edis
    -0.16
    ed
    -0.15
    ascript
    -0.15
    imizin
    -0.14
    parable
    -0.14
    -ing
    -0.14
    GED
    -0.14
    ед
    -0.14
    mÃ¼ÅŁ
    -0.14
    astically
    -0.14
    POSITIVE LOGITS
    ity
    1.09
    ities
    0.96
    ITY
    0.77
    ITIES
    0.59
    idade
    0.54
    ty
    0.53
    ality
    0.51
    idad
    0.51
    ties
    0.49
    ité
    0.46
    Activations Density 0.031%

    No Known Activations