© 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. 54426
    Prev
    Next
    INDEX
    Explanations

    terms related to criticism and critical assessment

    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
    dale
    -0.16
    UCE
    -0.14
    /autoload
    -0.13
    834
    -0.13
    SKTOP
    -0.13
    .SetActive
    -0.13
    efe
    -0.13
    nbsp
    -0.13
    readcr
    -0.13
    ihat
    -0.13
    POSITIVE LOGITS
     towards
    0.29
     toward
    0.26
     verso
    0.20
     Towards
    0.19
     both
    0.19
     hacia
    0.19
    Towards
    0.18
     attitude
    0.17
     Tow
    0.17
    oward
    0.16
    Activations Density 0.023%

    No Known Activations