© 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. 35067
    Prev
    Next
    INDEX
    Explanations

    line path configuration

    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
     acc
    -0.11
     sag
    -0.10
    quan
    -0.10
     Gad
    -0.10
     Ñģог
    -0.10
     Mend
    -0.09
    漫
    -0.09
     Rubio
    -0.09
     Edu
    -0.09
     riv
    -0.08
    POSITIVE LOGITS
     Facts
    0.17
     facts
    0.15
     absent
    0.13
    facts
    0.12
    infile
    0.12
    Absent
    0.12
     Ans
    0.11
    íĺ¸
    0.11
     Lair
    0.11
    Ans
    0.10
    Activations Density 0.020%

    No Known Activations