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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 44111
    Prev
    Next
    INDEX
    Explanations

    introduces a step or method

    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
     Isles
    -0.10
    isz
    -0.10
    469
    -0.10
     Isle
    -0.09
    gewater
    -0.09
    agi
    -0.09
     Andre
    -0.09
    ISA
    -0.09
    ulton
    -0.08
    zew
    -0.08
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.17
     is
    0.17
    çļĦæĺ¯
    0.17
     adalah
    0.16
     would
    0.15
     lÃł
    0.14
    æĺ¯
    0.14
     είναι
    0.14
    å°±æĺ¯
    0.14
    ëĬĶ
    0.13
    Activations Density 0.060%

    No Known Activations