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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Llama3.3-70B-IT (Instruct)
    3. 50-RESID-POST-GF
    4. 65196
    Prev
    Next
    INDEX
    Explanations

    handling variety, providing content

    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
    ungs
    -0.09
     aforementioned
    -0.08
    imus
    -0.08
    urement
    -0.08
    urg
    -0.08
    enz
    -0.08
    redis
    -0.08
    åįļ士
    -0.08
    Ë
    -0.08
    afa
    -0.08
    POSITIVE LOGITS
    ATAB
    0.10
     certain
    0.09
     ...\n\n\n\n
    0.09
     ancak
    0.09
    krv
    0.09
     versatility
    0.09
     möglich
    0.09
    795
    0.09
     flex
    0.09
     flexibility
    0.08
    Activations Density 0.155%

    No Known Activations