© 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. 49957
    Prev
    Next
    INDEX
    Explanations

    discontinued project

    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
    548
    -0.12
     cul
    -0.11
    eper
    -0.10
    ãĤ£
    -0.09
     throughout
    -0.09
     aff
    -0.08
     Eld
    -0.08
     Success
    -0.08
    opr
    -0.08
    uego
    -0.08
    POSITIVE LOGITS
     where
    0.18
     previous
    0.17
    where
    0.15
     Where
    0.15
     last
    0.14
     continuing
    0.14
     resume
    0.14
     donde
    0.14
    æĸŃ
    0.14
    Where
    0.14
    Activations Density 0.077%

    No Known Activations