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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65528
    Prev
    Next
    INDEX
    Explanations

    causes or effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.3-70B-IT @ 50-resid-post-gf
    Configuration
    Goodfire/Llama-3.3-70B-Instruct-SAE-l50/Llama-3.3-70B-Instruct-SAE-l50.pt
    Prompts (Dashboard)
    10,000 prompts, 128 tokens each
    Dataset (Dashboard)
    lmsys/lmsys-chat-1m
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discour
    -0.10
     succ
    -0.10
     ign
    -0.10
     Hood
    -0.09
    succ
    -0.09
     bes
    -0.09
    iny
    -0.09
     commande
    -0.08
    erce
    -0.08
    601
    -0.08
    POSITIVE LOGITS
     earned
    0.13
     cost
    0.11
     ostr
    0.11
    earned
    0.10
     soon
    0.10
     COST
    0.10
     ende
    0.10
    æĶ¾åľ¨
    0.10
    cost
    0.10
     landed
    0.10
    Activations Density 0.040%

    No Known Activations