© 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. 25429
    Prev
    Next
    INDEX
    Explanations

    dealing with consequences or intent

    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
     Tart
    -0.10
    uard
    -0.10
    zier
    -0.09
     piger
    -0.09
     ris
    -0.09
     onCancelled
    -0.09
     mastur
    -0.09
    VAS
    -0.09
     kred
    -0.09
     nons
    -0.09
    POSITIVE LOGITS
     peer
    0.15
     circumstances
    0.14
     actions
    0.13
     choices
    0.13
     acted
    0.13
     acting
    0.12
     ext
    0.11
     circum
    0.11
     Peer
    0.11
     Choices
    0.11
    Activations Density 0.082%

    No Known Activations