© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 19942
    Prev
    Next
    INDEX
    Explanations

    exposer

    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
     ниÑħ
    -0.13
     ihnen
    -0.12
    forman
    -0.10
     Ihnen
    -0.10
     तम
    -0.09
    Them
    -0.09
     reco
    -0.09
     ellos
    -0.09
    rita
    -0.09
    /if
    -0.09
    POSITIVE LOGITS
     la
    0.14
     effic
    0.11
    bbe
    0.10
     les
    0.10
    ÏĦαι
    0.10
    emo
    0.10
    ais
    0.10
     hale
    0.09
    azÄĥ
    0.09
    emos
    0.09
    Activations Density 0.141%

    No Known Activations