© 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. 43491
    Prev
    Next
    INDEX
    Explanations

    phrases and sentiments related to negative emotions and societal criticism

    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
     and
    -0.32
     or
    -0.30
    à¹ģละ
    -0.23
    æĪĸ
    -0.22
    and
    -0.22
     и
    -0.22
     vÃł
    -0.21
     или
    -0.20
     ë°ı
    -0.20
    à¹ģละส
    -0.20
    POSITIVE LOGITS
     instead
    0.15
     ÙĪÙĦÙĬ
    0.14
     depending
    0.14
     unlike
    0.14
     compared
    0.13
    à¹Ģà¸Ĺ
    0.13
    instead
    0.13
    iggs
    0.12
    depending
    0.12
     exactly
    0.11
    Activations Density 0.001%

    No Known Activations