© 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. 15559
    Prev
    Next
    INDEX
    Explanations

    skills and concepts

    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
     Mojo
    -0.10
    ãĢĢãĢĢãĢĢãĢĢ ãĢĢ
    -0.10
    gii
    -0.09
     potentially
    -0.09
     might
    -0.09
    ulance
    -0.08
     ?>\n\n\n
    -0.08
     addCriterion
    -0.08
    achat
    -0.08
     provid
    -0.08
    POSITIVE LOGITS
    æĺ¯æĪij
    0.10
    often
    0.09
     effectively
    0.09
     khiến
    0.09
    Always
    0.09
     genu
    0.09
    always
    0.08
     construct
    0.08
    963
    0.08
     tôi
    0.08
    Activations Density 0.075%

    No Known Activations