© 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. 23788
    Prev
    Next
    INDEX
    Explanations

    phrases related to budgetary policy and fiscal responsibility

    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
     derec
    -0.17
     fkk
    -0.16
    اÙĦØ¥ÙĨجÙĦÙĬزÙĬØ©
    -0.16
    adaÅŁ
    -0.15
    VERRIDE
    -0.15
    ีà¸ŀ
    -0.15
    มà¹Ģà¸ķ
    -0.15
    mojom
    -0.15
    ezier
    -0.15
    庫
    -0.14
    POSITIVE LOGITS
     Social
    0.27
     defense
    0.25
    Social
    0.23
     Defense
    0.22
     defence
    0.22
     Defence
    0.21
     Medicare
    0.21
    Ent
    0.20
     Ent
    0.20
     entitlement
    0.19
    Activations Density 0.060%

    No Known Activations