© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 43297
    Prev
    Next
    INDEX
    Explanations

    cold, cool, blood, humid

    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
     sunny
    -0.12
     thaw
    -0.11
     drying
    -0.10
     Coff
    -0.10
     Sunny
    -0.10
     rains
    -0.10
     rainy
    -0.09
     sunshine
    -0.09
     heated
    -0.09
    783
    -0.09
    POSITIVE LOGITS
     cold
    0.66
    cold
    0.56
    åĨ·
    0.54
     Cold
    0.53
    Cold
    0.50
     Ñħолод
    0.47
     cool
    0.42
     lạnh
    0.40
    å¯Ĵ
    0.39
     soÄŁuk
    0.38
    Activations Density 0.152%

    No Known Activations