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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29280
    Prev
    Next
    INDEX
    Explanations

    references to educational environments and concerns related to them

    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
    ToF
    -0.14
    νÏī
    -0.14
    _WARNINGS
    -0.14
    èĩªæ²»
    -0.14
    aturas
    -0.14
    @student
    -0.14
    .intellij
    -0.14
    _fds
    -0.13
    SWEP
    -0.13
     DVR
    -0.13
    POSITIVE LOGITS
     tech
    0.85
     technology
    0.73
     Tech
    0.70
     Technology
    0.68
    tech
    0.67
    -tech
    0.64
    Tech
    0.64
     technological
    0.64
     IT
    0.61
    Technology
    0.59
    Activations Density 0.038%

    No Known Activations