© 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. 50002
    Prev
    Next
    INDEX
    Explanations

    units and measurements followed by caveats

    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
    AndGet
    -0.08
    eli
    -0.08
    ãĥªãĤ«
    -0.08
     olduÄŁundan
    -0.08
     Because
    -0.08
    Because
    -0.08
     Oaks
    -0.07
    dit
    -0.07
    ))*(
    -0.07
    ystate
    -0.07
    POSITIVE LOGITS
     according
    0.16
    according
    0.11
     HOWEVER
    0.11
    ï¼Įä½Ĩæĺ¯
    0.11
     اÙĦبتÙĩ
    0.10
     Specifically
    0.10
    ãģŁãģł
    0.10
    However
    0.10
     specifically
    0.10
     згÑĸдно
    0.10
    Activations Density 0.226%

    No Known Activations