© 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. 43419
    Prev
    Next
    INDEX
    Explanations

    terms related to roles or positions, particularly in a bureaucratic or official context

    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
    ed
    -0.31
    es
    -0.23
    enden
    -0.22
    eners
    -0.21
    ened
    -0.20
    env
    -0.19
    edad
    -0.19
    ep
    -0.19
    eker
    -0.19
    ester
    -0.19
    POSITIVE LOGITS
    ship
    0.46
    ial
    0.39
    ially
    0.34
    ium
    0.33
    ships
    0.33
    ials
    0.31
    IAL
    0.28
    ily
    0.26
    SHIP
    0.25
    ious
    0.24
    Activations Density 0.021%

    No Known Activations