© 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. 55321
    Prev
    Next
    INDEX
    Explanations

    the fish to become

    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
     Beef
    -0.12
     beef
    -0.11
     duck
    -0.10
    Ymd
    -0.09
     Fibonacci
    -0.09
    _frm
    -0.09
     Trail
    -0.09
    Chicken
    -0.09
     trail
    -0.09
     Wire
    -0.09
    POSITIVE LOGITS
     fish
    0.24
     fil
    0.21
     caught
    0.19
     cod
    0.18
     Fish
    0.17
    é±¼
    0.17
     catch
    0.16
    fil
    0.16
     Atlantic
    0.16
     salmon
    0.16
    Activations Density 0.055%

    No Known Activations