© 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. 58488
    Prev
    Next
    INDEX
    Explanations

    protecting interests and rights

    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
    tainment
    -0.11
    inke
    -0.09
    393
    -0.09
     Rath
    -0.09
    paged
    -0.09
    apixel
    -0.09
    cmc
    -0.09
     NÄĽkter
    -0.09
     Fet
    -0.09
     tolerated
    -0.09
    POSITIVE LOGITS
     interests
    0.32
     integrity
    0.23
     rights
    0.22
     against
    0.21
    rights
    0.18
     reputation
    0.18
    åħį
    0.18
     khá»ıi
    0.18
    against
    0.17
     Against
    0.17
    Activations Density 0.047%

    No Known Activations