© 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. 9024
    Prev
    Next
    INDEX
    Explanations

    however and adversative conjunctions

    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
    ï¼ĮèĢĮä¸Ķ
    -0.15
     also
    -0.14
     ÐļÑĢÑĸм
    -0.14
    ä¸Ķ
    -0.14
    also
    -0.13
     Ayrıca
    -0.13
    Furthermore
    -0.13
     Також
    -0.13
    Ñıгом
    -0.12
    è¿ĺæľī
    -0.12
    POSITIVE LOGITS
     however
    0.55
     However
    0.53
    However
    0.50
     HOWEVER
    0.44
     однако
    0.40
     jedoch
    0.38
     Ðŀднако
    0.35
    ï¼Įä½Ĩæĺ¯
    0.35
    however
    0.34
     však
    0.33
    Activations Density 0.175%

    No Known Activations