© 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. 43461
    Prev
    Next
    INDEX
    Explanations

    contrast

    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
    dge
    -0.10
     overlaps
    -0.09
     Close
    -0.09
    kee
    -0.09
    leta
    -0.08
     è¦
    -0.08
     disput
    -0.08
    tÃŃ
    -0.08
     closely
    -0.08
    _ml
    -0.08
    POSITIVE LOGITS
     contrast
    0.68
     Contrast
    0.57
    contrast
    0.55
     contrasts
    0.41
    Contr
    0.39
     конÑĤÑĢа
    0.37
    _contr
    0.36
     CONTR
    0.34
     stark
    0.31
     пÑĢоÑĤивоп
    0.27
    Activations Density 0.118%

    No Known Activations