© 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. 36872
    Prev
    Next
    INDEX
    Explanations

    improved engine performance

    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
     hypers
    -0.11
     ydk
    -0.10
    .scalablytyped
    -0.10
     addCriterion
    -0.10
    eacher
    -0.09
    ÐIJÑĢÑħÑĸв
    -0.09
    PointCloud
    -0.09
     barn
    -0.09
    RGBO
    -0.09
     lab
    -0.09
    POSITIVE LOGITS
     engine
    0.21
     Hav
    0.15
     engines
    0.15
     Engine
    0.15
     Irr
    0.15
     Carm
    0.15
     middleware
    0.14
     irr
    0.12
     Stub
    0.12
     Direct
    0.12
    Activations Density 0.071%

    No Known Activations