© 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. 43749
    Prev
    Next
    INDEX
    Explanations

    references to political succession and leadership transitions

    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
    uspend
    -0.16
    ETO
    -0.16
    addtogroup
    -0.16
    ahun
    -0.14
    argas
    -0.14
    instein
    -0.14
    VRT
    -0.14
    edian
    -0.14
    bard
    -0.14
    ignon
    -0.14
    POSITIVE LOGITS
     successor
    0.53
     heir
    0.49
     succession
    0.45
     successors
    0.41
     heirs
    0.38
     inherit
    0.36
    继
    0.34
     replacement
    0.34
     inher
    0.33
     Replacement
    0.31
    Activations Density 0.042%

    No Known Activations