© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 1850
    Prev
    Next
    INDEX
    Explanations

    a description of a concept

    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
     yen
    -0.10
     hallmark
    -0.09
    iske
    -0.09
     tar
    -0.09
    abcdefghijkl
    -0.09
    751
    -0.09
     Brent
    -0.09
    iry
    -0.09
    .č\n\n
    -0.08
     prec
    -0.08
    POSITIVE LOGITS
     popular
    0.14
    popular
    0.10
     term
    0.10
    .examples
    0.10
     Popular
    0.10
     Sob
    0.10
    _async
    0.09
    ndx
    0.09
     addCriterion
    0.09
     prime
    0.09
    Activations Density 0.168%

    No Known Activations