© 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. 60389
    Prev
    Next
    INDEX
    Explanations

    life in prison

    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
     hostage
    -0.13
     Junk
    -0.11
    ROUT
    -0.10
     enslaved
    -0.10
     hostages
    -0.10
     Closet
    -0.10
     rout
    -0.10
     stranded
    -0.10
     captive
    -0.09
     prosecuting
    -0.09
    POSITIVE LOGITS
     prison
    0.34
     jail
    0.25
    çį
    0.20
     lock
    0.19
     ga
    0.19
    çī
    0.19
     sentence
    0.19
    arcer
    0.18
     serving
    0.18
     Prison
    0.18
    Activations Density 0.065%

    No Known Activations