© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Llama3.3-70B-IT
    5. 50-RESID-POST-GF
    7. 45055
    Prev
    Next
    INDEX
    Explanations

    jailbreak and prison contexts

    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
     jails
    -0.12
     imprisoned
    -0.12
     prisons
    -0.11
     imprisonment
    -0.11
     incarcerated
    -0.11
     incarceration
    -0.11
     Arrest
    -0.10
     arrests
    -0.10
     arrest
    -0.10
     imprison
    -0.10
    POSITIVE LOGITS
    break
    0.14
     cells
    0.13
    bird
    0.13
     yard
    0.13
    house
    0.12
     cell
    0.12
    ers
    0.12
    -yard
    0.12
     sentence
    0.12
    nier
    0.12
    Activations Density 0.022%

    No Known Activations