© 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. 29983
    Prev
    Next
    INDEX
    Explanations

    statements relating to concepts, ideas, and frameworks

    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
    Simply
    -0.23
     Simply
    -0.19
     simply
    -0.19
    à¹Ĥà¸Ĭ
    -0.16
    .expected
    -0.15
    abra
    -0.15
     will
    -0.15
     simplement
    -0.14
     же
    -0.14
     best
    -0.14
    POSITIVE LOGITS
     intriguing
    0.28
     certainly
    0.25
     interesting
    0.24
     wouldn
    0.24
     might
    0.24
     could
    0.24
     possibilities
    0.22
     possibility
    0.22
     Might
    0.21
    Interesting
    0.21
    Activations Density 0.048%

    No Known Activations