© 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. 42174
    Prev
    Next
    INDEX
    Explanations

    it is difficult

    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
    ahas
    -0.10
     Sharon
    -0.10
     |/
    -0.09
     Bru
    -0.09
     noe
    -0.09
    ãĥĭãĤ¢
    -0.09
    ContextHolder
    -0.09
     Dw
    -0.09
    Verdana
    -0.09
    tk
    -0.08
    POSITIVE LOGITS
     difficult
    0.21
     hard
    0.17
    iner
    0.15
     difÃŃcil
    0.15
     impossible
    0.14
     difficile
    0.14
     difÃŃc
    0.13
     ÑĤÑĢÑĥд
    0.13
     diffic
    0.12
     harder
    0.12
    Activations Density 0.035%

    No Known Activations