© 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. 55014
    Prev
    Next
    INDEX
    Explanations

    cruelty and rewards

    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
    •GENERAL
    Relentless?

    No Comments

    Negative Logits
    abant
    -0.12
     sacrific
    -0.11
     rever
    -0.09
     Sacr
    -0.09
    ..\n\n\n\n
    -0.09
    aiser
    -0.09
     because
    -0.09
    esp
    -0.09
     radi
    -0.09
     clin
    -0.09
    POSITIVE LOGITS
     cruel
    0.16
     cons
    0.14
     rewards
    0.14
     Cru
    0.14
     Rewards
    0.13
     conspir
    0.13
     itself
    0.13
     cruelty
    0.13
     reward
    0.13
    ollo
    0.11
    Activations Density 0.110%

    No Known Activations