© 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. 50924
    Prev
    Next
    INDEX
    Explanations

    steps or translation

    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
     form
    -0.12
     progressively
    -0.09
    itr
    -0.09
     sod
    -0.09
     Fro
    -0.09
     slim
    -0.08
     fro
    -0.08
     Gry
    -0.08
     Mont
    -0.08
     stub
    -0.08
    POSITIVE LOGITS
     one
    0.30
    one
    0.21
     satu
    0.19
     step
    0.19
    ä¸ĢæŃ¥
    0.19
    ä¸ĢçĤ¹
    0.18
     piece
    0.18
     bit
    0.16
    _one
    0.16
    ä¸Ģ页
    0.16
    Activations Density 0.146%

    No Known Activations