© 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. 28149
    Prev
    Next
    INDEX
    Explanations

    Generative AI models limited

    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
     failures
    -0.11
     actually
    -0.09
     consistent
    -0.09
     mere
    -0.09
     Hak
    -0.09
    ild
    -0.08
     Lynch
    -0.08
    ored
    -0.08
     Failure
    -0.08
    allow
    -0.08
    POSITIVE LOGITS
     limited
    0.41
    limited
    0.33
    Limited
    0.31
     Limited
    0.30
    æľīéĻIJ
    0.29
    åıªèĥ½
    0.28
     limitation
    0.27
     limitations
    0.27
     limits
    0.26
     LIMITED
    0.26
    Activations Density 0.087%

    No Known Activations