© 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. 8527
    Prev
    Next
    INDEX
    Explanations

    easily copied and pasted

    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
    EMPLARY
    -0.08
    _DIAG
    -0.08
    uns
    -0.08
    YST
    -0.08
    omet
    -0.08
    åħ³
    -0.08
    ivil
    -0.08
     Mahm
    -0.08
    èģ
    -0.07
    езÑĥлÑĮÑĤ
    -0.07
    POSITIVE LOGITS
     later
    0.18
    later
    0.15
     später
    0.13
    Later
    0.12
     easily
    0.12
     Later
    0.11
     future
    0.11
     potentially
    0.10
    åħ¸
    0.10
     pozdÄĽji
    0.10
    Activations Density 0.310%

    No Known Activations