© 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. 32293
    Prev
    Next
    INDEX
    Explanations

    ends of blocks or data processing

    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
    922
    -0.09
     Mog
    -0.08
    ermann
    -0.08
     fo
    -0.08
     dzie
    -0.08
     Mats
    -0.08
     derp
    -0.07
     Audi
    -0.07
    831
    -0.07
    tura
    -0.07
    POSITIVE LOGITS
    éĺħ读次æķ°
    0.09
    她çļĦ
    0.09
     her
    0.09
    è¾ij
    0.09
     his
    0.09
    ãĢģé«ĺ
    0.09
    æ½
    0.08
    ripp
    0.08
    ormsg
    0.08
    ¦æĥħ
    0.08
    Activations Density 0.045%

    No Known Activations