© 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. 54246
    Prev
    Next
    INDEX
    Explanations

    references to scientific concepts and methodologies

    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
    åĪļæīį
    -0.17
    ái
    -0.16
    endid
    -0.15
    ÐĴÑĤ
    -0.14
    icari
    -0.14
    pta
    -0.14
    utut
    -0.14
     EITHER
    -0.14
    ibold
    -0.13
    ulle
    -0.13
    POSITIVE LOGITS
     because
    0.36
    because
    0.30
     when
    0.28
     Because
    0.25
     porque
    0.25
     while
    0.23
    à¹Ģà¸ŀราะ
    0.23
    when
    0.23
    Because
    0.23
     instead
    0.21
    Activations Density 0.706%

    No Known Activations