© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 23091
    Prev
    Next
    INDEX
    Explanations

    negative descriptors and concepts associated with monstrosity or monstrous beings

    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
    éŃĤ
    -0.17
    949
    -0.15
     McKenzie
    -0.14
    akit
    -0.14
    enberg
    -0.14
    naissance
    -0.14
    hana
    -0.13
    igram
    -0.13
    hg
    -0.13
    ures
    -0.13
    POSITIVE LOGITS
     mon
    0.69
    -mon
    0.54
    mon
    0.52
     MON
    0.50
     Mon
    0.49
    _mon
    0.48
     beh
    0.47
    Mon
    0.46
     мон
    0.44
    .mon
    0.43
    Activations Density 0.037%

    No Known Activations