© 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. 1705
    Prev
    Next
    INDEX
    Explanations

    potential for harm or unethical action

    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
    ellig
    -0.10
    369
    -0.09
    erra
    -0.09
    nÃŃ
    -0.09
     Partial
    -0.09
    аниÑĨ
    -0.08
    unami
    -0.08
     Stall
    -0.08
    íĽĪ
    -0.08
     infect
    -0.08
    POSITIVE LOGITS
     might
    0.23
     could
    0.19
    might
    0.16
     would
    0.16
     könnte
    0.14
     Might
    0.14
     clearly
    0.13
     podrÃŃa
    0.12
    could
    0.12
     pourrait
    0.12
    Activations Density 0.046%

    No Known Activations