© 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. 43291
    Prev
    Next
    INDEX
    Explanations

    potential risks and outcomes

    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
    ì£
    -0.10
     adversely
    -0.10
    ä¸įå¾Ĺ
    -0.09
     uncomp
    -0.09
    KeySpec
    -0.09
     gaz
    -0.09
    én
    -0.09
    >(*
    -0.08
    okino
    -0.08
    EPROM
    -0.08
    POSITIVE LOGITS
     could
    0.40
    could
    0.32
     risk
    0.29
     Could
    0.28
     potentially
    0.28
     risks
    0.27
    Could
    0.27
     bisa
    0.24
     könnte
    0.22
     Ris
    0.22
    Activations Density 0.099%

    No Known Activations