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. 23656
    Prev
    Next
    INDEX
    Explanations

    concepts related to self-sacrifice and the willingness to endure hardships for others

    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
    alach
    -0.17
    icari
    -0.15
    roud
    -0.15
    /vendor
    -0.15
    Handled
    -0.14
    leigh
    -0.14
     cong
    -0.14
    _Default
    -0.14
    laz
    -0.14
    yper
    -0.14
    POSITIVE LOGITS
     sacrifice
    0.63
     sacrifices
    0.55
     sacr
    0.54
     Sacr
    0.54
     sacrificing
    0.49
     sacrific
    0.48
     sacrificed
    0.47
     SAC
    0.40
     sac
    0.38
    acr
    0.35
    Activations Density 0.051%

    No Known Activations