© 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. 51796
    Prev
    Next
    INDEX
    Explanations

    agua salada, lace tight

    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
     Elliott
    -0.10
    hausen
    -0.09
     Ensemble
    -0.09
     Mem
    -0.09
     :::
    -0.09
    å°ģ
    -0.08
     Persist
    -0.08
    ÑĢиÑĦ
    -0.08
     formal
    -0.08
     обол
    -0.08
    POSITIVE LOGITS
     el
    0.31
     Fra
    0.18
     column
    0.17
    uate
    0.15
     gradient
    0.15
     mobile
    0.15
    Fra
    0.15
    -el
    0.14
     fractions
    0.13
     Mobile
    0.13
    Activations Density 0.003%

    No Known Activations