© 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. 44743
    Prev
    Next
    INDEX
    Explanations

    negative or critical evaluations

    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
     safest
    -0.13
    INY
    -0.13
    à¸Ńà¸Ķ
    -0.13
    kees
    -0.13
     onCancelled
    -0.13
    à¹ĥà¸ļ
    -0.13
    ISIBLE
    -0.12
    κολ
    -0.12
    odash
    -0.12
     buc
    -0.12
    POSITIVE LOGITS
     good
    1.15
    good
    0.96
     GOOD
    0.87
     Good
    0.83
    -good
    0.82
    Good
    0.81
    _good
    0.73
    GOOD
    0.71
    .good
    0.70
    好
    0.67
    Activations Density 0.033%

    No Known Activations