© 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. 12602
    Prev
    Next
    INDEX
    Explanations

    ensure this success training

    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
     nurs
    -0.11
     Shemale
    -0.10
     Sexy
    -0.10
     inner
    -0.10
     supportive
    -0.09
    ､_
    -0.09
     sexes
    -0.09
    Sexy
    -0.09
    igans
    -0.09
     friendly
    -0.09
    POSITIVE LOGITS
     training
    0.21
     Training
    0.18
    training
    0.18
    -training
    0.16
    Training
    0.16
    è®Ń
    0.15
    (training
    0.15
    è¨ĵ
    0.14
    .training
    0.13
    TRAIN
    0.13
    Activations Density 0.024%

    No Known Activations