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. 23389
    Prev
    Next
    INDEX
    Explanations

    themes related to friendship and interpersonal relationships

    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
    å¿ł
    -0.16
    avy
    -0.15
    ournaments
    -0.15
    lyph
    -0.15
    ace
    -0.14
    ianne
    -0.14
    /shared
    -0.14
     Someone
    -0.14
    à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ
    -0.14
     Died
    -0.14
    POSITIVE LOGITS
     friends
    0.35
     partners
    0.28
     equals
    0.27
     colleagues
    0.27
     enemies
    0.27
     FRIEND
    0.27
     Friends
    0.26
     adversaries
    0.26
     teammates
    0.25
     allies
    0.25
    Activations Density 0.064%

    No Known Activations