Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 32846
    Prev
    Next
    INDEX
    Explanations

    terms related to volcanic eruptions and their consequences

    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
    AttributeValue
    -0.15
    466
    -0.15
     Bomb
    -0.14
    StringValue
    -0.14
     bombard
    -0.13
    aires
    -0.13
     Amerik
    -0.13
     DISCLAIMER
    -0.13
     dri
    -0.13
     Sharp
    -0.13
    POSITIVE LOGITS
     bill
    0.33
     smoke
    0.29
     pl
    0.29
     cloud
    0.28
     column
    0.28
     columns
    0.27
     clouds
    0.26
    -cloud
    0.25
     puff
    0.25
     pillar
    0.24
    Activations Density 0.064%

    No Known Activations