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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 15087
    Prev
    Next
    INDEX
    Explanations

    his skills summarize profile

    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
     ple
    -0.09
     ï½
    -0.08
    ihan
    -0.08
    unlikely
    -0.08
     unlikely
    -0.08
    à¤ľà¤°
    -0.08
    already
    -0.08
    itos
    -0.08
    lescope
    -0.08
     Viking
    -0.08
    POSITIVE LOGITS
     contributions
    0.11
     presence
    0.10
     leadership
    0.10
    yme
    0.09
     Contributions
    0.09
    :convert
    0.09
    osed
    0.09
    ymes
    0.09
    Availability
    0.09
     slack
    0.09
    Activations Density 0.026%

    No Known Activations