Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Julius Han · Gated SAE for Llama3-8B-Instruct
    3. Llama3-8B-IT
    4. Residual Stream
    5. 25-RES-JH
    6. 23498
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate future direction or progression

    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
    igner
    -0.18
    elson
    -0.18
    umo
    -0.16
    zcze
    -0.16
    uego
    -0.15
    emoc
    -0.15
    edback
    -0.15
     ongoing
    -0.15
    é¡Ķ
    -0.14
    psy
    -0.14
    POSITIVE LOGITS
    SSIP
    0.19
    ÅĤÄħ
    0.18
     Wrong
    0.17
     wrong
    0.17
    VERN
    0.17
    -ahead
    0.16
    erno
    0.16
    isser
    0.16
     Tos
    0.15
    -next
    0.15
    Activations Density 0.028%

    No Known Activations