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. 44787
    Prev
    Next
    INDEX
    Explanations

    number of epochs

    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
     Kund
    -0.09
     eins
    -0.09
    ARC
    -0.08
     Conc
    -0.08
    uf
    -0.08
    iversite
    -0.08
    uces
    -0.08
     bran
    -0.08
     Cir
    -0.08
    Interval
    -0.08
    POSITIVE LOGITS
     rounds
    0.19
     steps
    0.15
     round
    0.15
     iterations
    0.14
     epochs
    0.14
    Steps
    0.14
     number
    0.13
     runs
    0.13
     Rounds
    0.13
     run
    0.13
    Activations Density 0.075%

    No Known Activations