© 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. 38122
    Prev
    Next
    INDEX
    Explanations

    client and software

    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
    oma
    -0.09
    ::::|
    -0.09
     Script
    -0.09
    zym
    -0.09
     Jensen
    -0.09
    bsite
    -0.09
     Website
    -0.09
    Wizard
    -0.09
    alf
    -0.09
     Crane
    -0.09
    POSITIVE LOGITS
     client
    0.24
     software
    0.23
     clients
    0.18
    software
    0.17
    client
    0.16
     app
    0.16
    客æĪ·
    0.16
     Software
    0.15
    软件
    0.15
     klient
    0.15
    Activations Density 0.155%

    No Known Activations