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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT (Instruct)
    5. 50-RESID-POST-GF
    7. 44532
    Prev
    Next
    INDEX
    Explanations

    reverse order or inverse reading

    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
    ^n
    -0.11
     Rowe
    -0.10
    olu
    -0.09
    erer
    -0.09
    ashboard
    -0.08
     substitutes
    -0.08
    =
    -0.08
     outr
    -0.08
     Altern
    -0.08
     Panc
    -0.08
    POSITIVE LOGITS
     reverse
    0.59
     reversed
    0.57
     Reverse
    0.50
    Reverse
    0.47
    reverse
    0.46
    éĢĨ
    0.45
     reversal
    0.44
     reversing
    0.41
    .reverse
    0.41
     revers
    0.38
    Activations Density 0.181%

    No Known Activations