© 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. 1823
    Prev
    Next
    INDEX
    Explanations

    fully capitalize, use effectively, ensure safety

    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
     Thornton
    -0.10
     fo
    -0.09
    eyer
    -0.09
    æ¾
    -0.09
     Saul
    -0.09
    oret
    -0.09
    'gc
    -0.08
     ob
    -0.08
    483
    -0.08
     des
    -0.08
    POSITIVE LOGITS
    æľĢ大
    0.23
    max
    0.22
    Max
    0.21
    -max
    0.21
     maximum
    0.20
     fully
    0.19
     Max
    0.19
    .max
    0.18
    MAX
    0.18
    _max
    0.18
    Activations Density 0.091%

    No Known Activations