© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 23996
    Prev
    Next
    INDEX
    Explanations

    for each

    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
    IFI
    -0.10
    751
    -0.09
    elper
    -0.09
    çļĦè¯Ŀ
    -0.09
     troub
    -0.09
    دÙĪاج
    -0.08
    .bunifuFlatButton
    -0.08
    ificate
    -0.08
    خب
    -0.08
    274
    -0.08
    POSITIVE LOGITS
    æĿ¥è¯´
    0.21
     sake
    0.18
     purposes
    0.15
     there
    0.11
     hãy
    0.10
     except
    0.10
    YD
    0.10
    aco
    0.09
    ulle
    0.09
    essa
    0.09
    Activations Density 0.097%

    No Known Activations