© 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. 43968
    Prev
    Next
    INDEX
    Explanations

    mentions of specific organizations and their affiliations in a legal 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
    .rd
    -0.15
    èĩ£
    -0.15
    æĿ¾
    -0.14
     Tee
    -0.14
    PostBack
    -0.14
    ocol
    -0.14
    odus
    -0.14
    OMATIC
    -0.14
     Rockefeller
    -0.14
    asje
    -0.14
    POSITIVE LOGITS
    Tro
    0.20
    tro
    0.19
     Trotsky
    0.19
    WS
    0.18
     Tro
    0.18
     WS
    0.18
     MLM
    0.18
     tro
    0.18
     Fight
    0.17
    Fight
    0.17
    Activations Density 0.072%

    No Known Activations