© 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. 3387
    Prev
    Next
    INDEX
    Explanations

    lists followed by purpose or continuation

    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
     include
    -0.11
    odon
    -0.10
    ï¼Įæ¯Ķ
    -0.10
     vÄįetnÄĽ
    -0.10
     such
    -0.10
     like
    -0.10
    åĮħæĭ¬
    -0.09
    oden
    -0.09
    ersed
    -0.09
    799
    -0.09
    POSITIVE LOGITS
     etc
    0.22
    etc
    0.21
     коÑĤоÑĢÑĭе
    0.14
    ãģªãģ©
    0.14
    ëĵ±
    0.14
    which
    0.13
     which
    0.12
    ãģªãģ©ãģ®
    0.11
     serta
    0.11
    çŃī
    0.11
    Activations Density 0.049%

    No Known Activations