© 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. 43811
    Prev
    Next
    INDEX
    Explanations

    shell commands and variables

    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
    =}
    -0.10
    urry
    -0.10
     ､
    -0.09
     Bride
    -0.08
    ACHE
    -0.08
    urge
    -0.08
     =
    -0.08
    {}
    -0.08
     Mons
    -0.08
     fel
    -0.08
    POSITIVE LOGITS
    OPTARG
    0.14
    ayah
    0.10
    '\
    0.10
    HOME
    0.10
     Sham
    0.09
     Hancock
    0.09
    ("$
    0.09
     âĪ¨
    0.09
    raci
    0.09
    line
    0.09
    Activations Density 0.012%

    No Known Activations