© 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. 9939
    Prev
    Next
    INDEX
    Explanations

    methods and techniques

    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
     methodology
    -0.11
     regime
    -0.09
    otel
    -0.09
    è¢ĸ
    -0.08
     æĢ§
    -0.08
     funkci
    -0.08
     dÄ±ÅŁÄ±
    -0.08
    mae
    -0.08
     BASIS
    -0.08
     Targets
    -0.08
    POSITIVE LOGITS
     techniques
    0.49
     methods
    0.49
     approaches
    0.39
     strategies
    0.38
    methods
    0.35
     Methods
    0.32
     technique
    0.32
    æĸ¹æ³ķ
    0.32
     Techniques
    0.31
     tactics
    0.30
    Activations Density 0.267%

    No Known Activations