© 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. 16056
    Prev
    Next
    INDEX
    Explanations

    contrary opposite reversal

    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
    kir
    -0.10
    idor
    -0.09
     Arb
    -0.09
     autom
    -0.09
    amic
    -0.08
     concent
    -0.08
    aper
    -0.08
    erk
    -0.08
     Äijâu
    -0.08
    allet
    -0.08
    POSITIVE LOGITS
     opposite
    0.74
     contrario
    0.45
     contrary
    0.44
     naopak
    0.43
     ngược
    0.41
     reverse
    0.36
     пÑĢоÑĤивоп
    0.35
     oppos
    0.34
    éĢĨ
    0.30
    reverse
    0.26
    Activations Density 0.128%

    No Known Activations