© 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. 40074
    Prev
    Next
    INDEX
    Explanations

    greater good

    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
     remainder
    -0.10
    .PO
    -0.09
     strong
    -0.09
    DCF
    -0.09
    лÑıв
    -0.08
     BCM
    -0.08
    hq
    -0.08
     ï¼į
    -0.08
    yg
    -0.08
    amic
    -0.08
    POSITIVE LOGITS
     good
    0.40
     GOOD
    0.29
    good
    0.29
     Good
    0.29
    Good
    0.28
    åĸĦ
    0.27
     benefit
    0.27
    GOOD
    0.25
    -good
    0.24
    好
    0.24
    Activations Density 0.066%

    No Known Activations