© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 693
    Prev
    Next
    INDEX
    Explanations

    variation

    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
     discrepancy
    -0.13
     discrepan
    -0.11
     Ryder
    -0.11
     discrepancies
    -0.10
     Alma
    -0.10
     mismatch
    -0.09
    umer
    -0.09
     Ston
    -0.09
     divergence
    -0.09
     cứ
    -0.09
    POSITIVE LOGITS
     variation
    0.38
     Variation
    0.31
     variations
    0.29
     var
    0.29
    variation
    0.28
     variability
    0.28
    Vari
    0.28
    _variation
    0.27
     Vari
    0.27
     vari
    0.26
    Activations Density 0.117%

    No Known Activations