© 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. 24062
    Prev
    Next
    INDEX
    Explanations

    references to funding, contributing, and the allocation of financial resources for projects

    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
    ãģĭãĤĬ
    -0.16
    oms
    -0.15
    FetchRequest
    -0.15
    è¡
    -0.14
    _fetch
    -0.14
     borrow
    -0.14
     borrowing
    -0.14
    å¥
    -0.14
    936
    -0.14
    935
    -0.14
    POSITIVE LOGITS
     directly
    0.29
     towards
    0.27
     rein
    0.24
     toward
    0.23
     direct
    0.21
     Towards
    0.19
     goes
    0.19
    oward
    0.19
    owards
    0.18
     invested
    0.18
    Activations Density 0.052%

    No Known Activations