© 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. 23868
    Prev
    Next
    INDEX
    Explanations

    concerns related to details and constraints in procedural or technical contexts

    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
     preceding
    -0.15
    preced
    -0.14
     firsthand
    -0.14
     hereby
    -0.14
    iloc
    -0.14
    autoreleasepool
    -0.14
    -prepend
    -0.13
     therein
    -0.13
    [:-
    -0.13
    ÙĬج
    -0.13
    POSITIVE LOGITS
     later
    1.28
    later
    1.06
     Later
    1.02
    Later
    0.99
     später
    0.84
     pozdÄĽji
    0.69
    åIJİ
    0.66
     latter
    0.66
     afterwards
    0.65
    å¾Įãģ«
    0.63
    Activations Density 0.023%

    No Known Activations