© 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. 4105
    Prev
    Next
    INDEX
    Explanations

    but, except, difference

    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
     brav
    -0.10
    601
    -0.10
     compared
    -0.09
    æīį
    -0.09
     dov
    -0.09
    692
    -0.09
    udit
    -0.08
    stad
    -0.08
    DOB
    -0.08
    orde
    -0.08
    POSITIVE LOGITS
     except
    0.44
    except
    0.38
     Except
    0.32
    Except
    0.29
     but
    0.27
    \texcept
    0.24
    _except
    0.23
     difference
    0.23
     nhÆ°ng
    0.23
     но
    0.21
    Activations Density 0.121%

    No Known Activations