© 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. 30479
    Prev
    Next
    INDEX
    Explanations

    freedom from torture and cruel treatment

    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
     constitutional
    -0.10
    etta
    -0.10
    åĸľ
    -0.09
    _virtual
    -0.09
    aska
    -0.09
    elage
    -0.09
    ãģħ
    -0.09
    142
    -0.08
     Horm
    -0.08
    aku
    -0.08
    POSITIVE LOGITS
     torture
    0.15
     TORT
    0.13
     Tort
    0.12
     right
    0.11
     shelter
    0.10
     dignity
    0.10
    imas
    0.10
     tortured
    0.10
     Right
    0.10
     dign
    0.10
    Activations Density 0.025%

    No Known Activations