© 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. 57028
    Prev
    Next
    INDEX
    Explanations

    suggesting qualitative codes for CVD

    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
     surveyed
    -0.12
     survey
    -0.12
     tun
    -0.10
     surveys
    -0.10
     Survey
    -0.09
     rop
    -0.09
     metrics
    -0.09
     experimental
    -0.09
     Giles
    -0.09
     metric
    -0.09
    POSITIVE LOGITS
     coding
    0.18
    Qual
    0.16
     triang
    0.16
     Qual
    0.16
    qual
    0.15
     Coding
    0.15
     saturation
    0.15
     Yin
    0.15
     snow
    0.15
     qualitative
    0.15
    Activations Density 0.054%

    No Known Activations