© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 34654
    Prev
    Next
    INDEX
    Explanations

    training AI models

    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
    549
    -0.11
     oath
    -0.09
    irit
    -0.09
    éri
    -0.09
     Sik
    -0.08
     Thomson
    -0.08
     McL
    -0.08
    ensi
    -0.08
     bubbles
    -0.08
    ãĢĢr
    -0.08
    POSITIVE LOGITS
     model
    0.15
     models
    0.14
     train
    0.10
     parameters
    0.10
     neural
    0.10
     network
    0.10
    ErrorException
    0.10
     networks
    0.10
    (train
    0.09
    /train
    0.09
    Activations Density 0.101%

    No Known Activations