© 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. 14569
    Prev
    Next
    INDEX
    Explanations

    information related to violent incidents and casualties

    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
     Weeks
    -0.18
     Week
    -0.17
     month
    -0.17
     Month
    -0.16
     Months
    -0.16
     Woche
    -0.16
     semana
    -0.15
    Month
    -0.15
    ên
    -0.14
    itere
    -0.14
    POSITIVE LOGITS
     around
    0.66
    around
    0.59
     Around
    0.54
    Around
    0.53
    -around
    0.45
     late
    0.40
     early
    0.38
     kolem
    0.37
     shortly
    0.34
     около
    0.33
    Activations Density 0.104%

    No Known Activations