© 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. 19646
    Prev
    Next
    INDEX
    Explanations

    but with increasing

    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
     twice
    -0.11
    ennes
    -0.10
    iras
    -0.09
    asm
    -0.09
    icz
    -0.09
    çĢ
    -0.09
     suddenly
    -0.09
     immedi
    -0.08
    ãģªãĤī
    -0.08
     Suddenly
    -0.08
    POSITIVE LOGITS
     eventually
    0.27
     Grad
    0.26
     dần
    0.25
     Eventually
    0.24
    Eventually
    0.23
     поÑģÑĤеп
    0.23
    æ¸IJ
    0.23
    Grad
    0.23
    vertime
    0.22
     overtime
    0.22
    Activations Density 0.148%

    No Known Activations